Emergence of Hierarchical Emotion Organization in Large Language Models Article Swipe
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2507.10599
As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for ethical deployment. Inspired by emotion wheels -- a psychological framework that argues emotions organize hierarchically -- we analyze probabilistic dependencies between emotional states in model outputs. We find that LLMs naturally form hierarchical emotion trees that align with human psychological models, and larger models develop more complex hierarchies. We also uncover systematic biases in emotion recognition across socioeconomic personas, with compounding misclassifications for intersectional, underrepresented groups. Human studies reveal striking parallels, suggesting that LLMs internalize aspects of social perception. Beyond highlighting emergent emotional reasoning in LLMs, our results hint at the potential of using cognitively-grounded theories for developing better model evaluations.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2507.10599
- https://arxiv.org/pdf/2507.10599
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414942746
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414942746Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2507.10599Digital Object Identifier
- Title
-
Emergence of Hierarchical Emotion Organization in Large Language ModelsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-07-12Full publication date if available
- Authors
-
Bo Zhao, Maya Okawa, Eric Bigelow, Rose Yu, Tomer Ullman, Ekdeep Singh Lubana, Hidenori TanakaList of authors in order
- Landing page
-
https://arxiv.org/abs/2507.10599Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2507.10599Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2507.10599Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414942746 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2507.10599 |
| ids.doi | https://doi.org/10.48550/arxiv.2507.10599 |
| ids.openalex | https://openalex.org/W4414942746 |
| fwci | |
| type | preprint |
| title | Emergence of Hierarchical Emotion Organization in Large Language Models |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.6656000018119812 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2507.10599 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2507.10599 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2507.10599 |
| locations[1].id | doi:10.48550/arxiv.2507.10599 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2507.10599 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5012513662 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-2890-1850 |
| authorships[0].author.display_name | Bo Zhao |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhao, Bo |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5059360988 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9525-166X |
| authorships[1].author.display_name | Maya Okawa |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Okawa, Maya |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5027500446 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Eric Bigelow |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Bigelow, Eric J. |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5057778679 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8491-7937 |
| authorships[3].author.display_name | Rose Yu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Yu, Rose |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5086092571 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-1722-2382 |
| authorships[4].author.display_name | Tomer Ullman |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ullman, Tomer |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5069090559 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-7200-9341 |
| authorships[5].author.display_name | Ekdeep Singh Lubana |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Lubana, Ekdeep Singh |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5101548632 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-2265-8885 |
| authorships[6].author.display_name | Hidenori Tanaka |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Tanaka, Hidenori |
| authorships[6].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2507.10599 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Emergence of Hierarchical Emotion Organization in Large Language Models |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.6656000018119812 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2507.10599 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2507.10599 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2507.10599 |
| primary_location.id | pmh:oai:arXiv.org:2507.10599 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2507.10599 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2507.10599 |
| publication_date | 2025-07-12 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 26 |
| abstract_inverted_index.-- | 25, 34 |
| abstract_inverted_index.As | 0 |
| abstract_inverted_index.We | 45, 67 |
| abstract_inverted_index.at | 108 |
| abstract_inverted_index.by | 22 |
| abstract_inverted_index.in | 42, 72, 103 |
| abstract_inverted_index.is | 16 |
| abstract_inverted_index.of | 95, 111 |
| abstract_inverted_index.we | 35 |
| abstract_inverted_index.and | 60 |
| abstract_inverted_index.for | 18, 81, 115 |
| abstract_inverted_index.how | 10 |
| abstract_inverted_index.our | 105 |
| abstract_inverted_index.the | 109 |
| abstract_inverted_index.LLMs | 48, 92 |
| abstract_inverted_index.also | 68 |
| abstract_inverted_index.find | 46 |
| abstract_inverted_index.form | 50 |
| abstract_inverted_index.hint | 107 |
| abstract_inverted_index.more | 64 |
| abstract_inverted_index.that | 29, 47, 54, 91 |
| abstract_inverted_index.they | 11 |
| abstract_inverted_index.with | 56, 78 |
| abstract_inverted_index.Human | 85 |
| abstract_inverted_index.LLMs, | 104 |
| abstract_inverted_index.align | 55 |
| abstract_inverted_index.human | 57 |
| abstract_inverted_index.large | 1 |
| abstract_inverted_index.model | 12, 43, 118 |
| abstract_inverted_index.power | 6 |
| abstract_inverted_index.trees | 53 |
| abstract_inverted_index.using | 112 |
| abstract_inverted_index.(LLMs) | 4 |
| abstract_inverted_index.Beyond | 98 |
| abstract_inverted_index.across | 75 |
| abstract_inverted_index.argues | 30 |
| abstract_inverted_index.better | 117 |
| abstract_inverted_index.biases | 71 |
| abstract_inverted_index.larger | 61 |
| abstract_inverted_index.models | 3, 62 |
| abstract_inverted_index.reveal | 87 |
| abstract_inverted_index.social | 96 |
| abstract_inverted_index.states | 15, 41 |
| abstract_inverted_index.users' | 13 |
| abstract_inverted_index.wheels | 24 |
| abstract_inverted_index.agents, | 8 |
| abstract_inverted_index.analyze | 36 |
| abstract_inverted_index.aspects | 94 |
| abstract_inverted_index.between | 39 |
| abstract_inverted_index.complex | 65 |
| abstract_inverted_index.develop | 63 |
| abstract_inverted_index.emotion | 23, 52, 73 |
| abstract_inverted_index.ethical | 19 |
| abstract_inverted_index.groups. | 84 |
| abstract_inverted_index.models, | 59 |
| abstract_inverted_index.results | 106 |
| abstract_inverted_index.studies | 86 |
| abstract_inverted_index.uncover | 69 |
| abstract_inverted_index.Inspired | 21 |
| abstract_inverted_index.critical | 17 |
| abstract_inverted_index.emergent | 100 |
| abstract_inverted_index.emotions | 31 |
| abstract_inverted_index.language | 2 |
| abstract_inverted_index.organize | 32 |
| abstract_inverted_index.outputs. | 44 |
| abstract_inverted_index.striking | 88 |
| abstract_inverted_index.theories | 114 |
| abstract_inverted_index.emotional | 14, 40, 101 |
| abstract_inverted_index.framework | 28 |
| abstract_inverted_index.naturally | 49 |
| abstract_inverted_index.personas, | 77 |
| abstract_inverted_index.potential | 110 |
| abstract_inverted_index.reasoning | 102 |
| abstract_inverted_index.developing | 116 |
| abstract_inverted_index.parallels, | 89 |
| abstract_inverted_index.suggesting | 90 |
| abstract_inverted_index.systematic | 70 |
| abstract_inverted_index.compounding | 79 |
| abstract_inverted_index.deployment. | 20 |
| abstract_inverted_index.internalize | 93 |
| abstract_inverted_index.perception. | 97 |
| abstract_inverted_index.recognition | 74 |
| abstract_inverted_index.dependencies | 38 |
| abstract_inverted_index.evaluations. | 119 |
| abstract_inverted_index.hierarchical | 51 |
| abstract_inverted_index.hierarchies. | 66 |
| abstract_inverted_index.highlighting | 99 |
| abstract_inverted_index.increasingly | 5 |
| abstract_inverted_index.probabilistic | 37 |
| abstract_inverted_index.psychological | 27, 58 |
| abstract_inverted_index.socioeconomic | 76 |
| abstract_inverted_index.understanding | 9 |
| abstract_inverted_index.conversational | 7 |
| abstract_inverted_index.hierarchically | 33 |
| abstract_inverted_index.intersectional, | 82 |
| abstract_inverted_index.underrepresented | 83 |
| abstract_inverted_index.misclassifications | 80 |
| abstract_inverted_index.cognitively-grounded | 113 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |