Emotion Entanglement and Bayesian Inference for Multi-Dimensional Emotion Understanding

TL;DR

This paper introduces EmoScene, a complex benchmark for multi-dimensional emotion understanding in context-rich scenarios, and proposes a Bayesian inference framework to improve emotion prediction consistency.

Contribution

It presents a new benchmark with structured emotion annotations and a novel entanglement-aware Bayesian inference method for better emotion prediction in language models.

Findings

Best model achieved a Macro F1 of 0.501 on EmoScene.

Bayesian inference improved weaker models' performance by +0.051 Macro F1.

EmoScene challenges current models to understand multi-dimensional, context-dependent emotions.

Abstract

Understanding emotions in natural language is inherently a multi-dimensional reasoning problem, where multiple affective signals interact through context, interpersonal relations, and situational cues. However, most existing emotion understanding benchmarks rely on short texts and predefined emotion labels, reducing this process to independent label prediction and ignoring the structured dependencies among emotions. To address this limitation, we introduce Emotional Scenarios (EmoScene), a theory-grounded benchmark of 4,731 context-rich scenarios annotated with an 8-dimensional emotion vector derived from Plutchik's basic emotions. We evaluate six instruction-tuned large language models in a zero-shot setting and observe modest performance, with the best model achieving a Macro F1 of 0.501, highlighting the difficulty of context-aware multi-label emotion prediction. Motivated by the observation that emotions rarely occur independently, we further propose an entanglement-aware Bayesian inference framework that incorporates emotion co-occurrence statistics to perform joint posterior inference over the emotion vector. This lightweight post-processing improves structural consistency of predictions and yields notable gains for weaker models (e.g., +0.051 Macro F1 for Qwen2.5-7B). EmoScene therefore provides a challenging benchmark for studying multi-dimensional emotion understanding and the limitations of current language models.