Emergence of Hierarchical Emotion Organization in Large Language Models

TL;DR

This paper investigates how large language models naturally develop hierarchical emotional structures similar to psychological models, revealing their emergent emotional reasoning and biases across social groups.

Contribution

It demonstrates that LLMs form hierarchical emotion trees aligned with human psychology and uncovers biases in emotion recognition related to socioeconomic and intersectional identities.

Findings

LLMs form hierarchical emotion trees similar to psychological models.

Larger models develop more complex emotional hierarchies.

Systematic biases in emotion recognition are present across social groups.

Abstract

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.