Emergence of Hierarchical Emotion Organization in Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915389836886016 |
|---|---|
| author | Zhao, Bo Okawa, Maya Bigelow, Eric J. Yu, Rose Ullman, Tomer Lubana, Ekdeep Singh Tanaka, Hidenori |
| author_facet | Zhao, Bo Okawa, Maya Bigelow, Eric J. Yu, Rose Ullman, Tomer Lubana, Ekdeep Singh Tanaka, Hidenori |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10599 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Emergence of Hierarchical Emotion Organization in Large Language Models Zhao, Bo Okawa, Maya Bigelow, Eric J. Yu, Rose Ullman, Tomer Lubana, Ekdeep Singh Tanaka, Hidenori Computation and Language Artificial Intelligence Machine Learning 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. |
| title | Emergence of Hierarchical Emotion Organization in Large Language Models |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.10599 |