Information-Theoretic Free Energy as Emotion Potential: Emotional Valence as a Function of Complexity and Novelty
This work addresses the problem of mathematically modeling emotional valence for researchers in computational neuroscience and psychology, but it is incremental as it builds directly on a previous model.
The study extended a prior mathematical model of emotion dimensions by incorporating perceived complexity alongside novelty as sources of arousal potential, modeling it as sensory surprisal equivalent to free energy, and provided empirical evidence with visual stimuli showing that the summation of novelty and complexity shapes an inverse U-shaped beauty function.
This study extends the mathematical model of emotion dimensions that we previously proposed (Yanagisawa, et al. 2019, Front Comput Neurosci) to consider perceived complexity as well as novelty, as a source of arousal potential. Berlyne's hedonic function of arousal potential (or the inverse U-shaped curve, the so-called Wundt curve) is assumed. We modeled the arousal potential as information contents to be processed in the brain after sensory stimuli are perceived (or recognized), which we termed sensory surprisal. We mathematically demonstrated that sensory surprisal represents free energy, and it is equivalent to a summation of information gain (or information from novelty) and perceived complexity (or information from complexity), which are the collative variables forming the arousal potential. We demonstrated empirical evidence with visual stimuli (profile shapes of butterfly) supporting the hypothesis that the summation of perceived novelty and complexity shapes the inverse U-shaped beauty function. We discussed the potential of free energy as a mathematical principle explaining emotion initiators.