Decoding Naturalistic Emotion Dynamics from the Brain: An LLM-Enhanced Regression Framework

2026-06-05

AI Summary

Traditional emotion decoding often relies on discrete single-label classification, which fails to capture the continuous, dynamic, and co-occurring nature of emotional states. This work proposes a multi-target regression framework that leverages large language models (LLMs) to generate fine-grained, continuous affective annotations from naturalistic auditory narratives for the first time. Integrating dynamic functional connectivity (DFC), regularization techniques, and kernel-based machine learning models, the approach enables real-time tracking of emotional dynamics in fMRI neural activity. Models based on DFC significantly outperform those using static region-of-interest amplitude representations, effectively capturing rapidly evolving emotional trajectories. Furthermore, by incorporating graph-theoretic explainable AI methods, the study reveals emotion-specific brain network topologies, offering neural evidence supporting psychological constructionist theories of emotion.

Abstract

Decoding emotional states from neural signals has been typically framed as a discrete, single-label classification task based on emotionally stable stimuli, a formulation that oversimplifies the continuous, fluid, and co-occurring nature of human affect. This study reconceptualizes emotion decoding by adopting a multi-target regression framework to track multiple overlapping emotional dimensions as continuous trajectories over time. Leveraging the robust generalization capabilities of Large Language Models (LLMs), we extracted fine-grained, continuous sentiment profiles from a naturalistic auditory narrative, Alice in Wonderland, to serve as scalable proxies for subjective affect from human fMRI dataset. Departing from standard classification paradigms or mass-univariate subtractive contrasts that filter out network dynamics, we leverage regularized and kernel-based machine learning algorithms as continuous estimators to track the magnitude of macroscale neural state variations. We demonstrate that models trained on temporal snapshots of Dynamic Functional Connectivity (DFC) significantly outperform static region-of-interest (ROI) amplitude representations, effectively capturing continuous emotional trajectories under rapidly fluctuating narrative input. Furthermore, by implementing graph-theoretical Explainable AI (XAI) techniques, we deconstruct the underlying predictive features to reveal highly interpretable, emotion-specific topological configurations. Collectively, these results highlight the utility of LLM-automated annotation in affective neuroscience and provide compelling empirical evidence for psychological constructionist frameworks, demonstrating that dynamic, distributed network interactions offer superior explanatory power over strictly locationist accounts of emotion.

Problem

• emotion decoding
• naturalistic stimuli
• continuous emotion
• dynamic functional connectivity
• affective neuroscience

Innovation

• LLM-enhanced regression
• Dynamic Functional Connectivity
• continuous emotion decoding
• Explainable AI
• naturalistic neuroscience