ascertaining, by at least one processor, an occurrence of an event in a virtual environment associated with an Artificial Intelligence (AI) character model, the AI character model being associated with a plurality of narratives and configured to generate an AI character for interaction with a user in the virtual environment;

analyzing the event, by the at least one processor, to produce, based on the event, a word embedding;

passing, by the at least one processor, the word embedding through a plurality of heuristics machine learning models to produce intermediate outputs of the plurality of heuristics machine learning models, the intermediate outputs of the plurality of heuristics machine learning models including one or more narrative triggers, the one or more narrative triggers being triggered based on information shared in a conversation between the AI character and the user in the virtual environment;

in response to the triggering of the one or more narrative triggers, selecting, by the at least one processor, a narrative from the plurality of narratives;

determining, by the at least one processor and based on the selected narrative, behavioral settings; and

applying, by the at least one processor, the behavioral settings to the AI character model, thereby causing the AI character model to follow the narrative in interactions with the user in the virtual environment, wherein the applying the behavioral settings includes: