Mental State Transition Network which consists of mental states connected one another is a
basic concept of approximating to human psychological and mental responses. It can represent transition
from an emotional state to other one with stimulus by calculating Emotion Generating Calculations
method. However, this method ignores most of emotions except for an emotion which has the strongest
effect in spite that EGC can calculate intensities of 20 emotions in parallel. Furthermore, grouping of the
emotions may be different among agents. In this paper, we propose a method to classify emotions
calculated by EGC using Self Organizing Map. Mental state transits based on the group of emotions on
the map. For example, a set of emotions in a group transits the mental state ``happy,'' and negative
mental state is enfeebled.