Interactive narratives are used for an ever-expanding array of purposes: educational lessons, training simulations, and even organizational behaviors have had narratives woven around them because these are made more compelling in a dramatic framing. Despite their ubiquity, they remain time-consuming, expensive, and technically challenging to engineer. The automated creation of narrative content, otherwise known as procedural narrative generation, stands poised to ameliorate this challenge. However, current artificial intelligence techniques remain agnostic of the user’s narratively-oriented cognitive faculties, which are important for the effective design of interactive narrative experiences. In this talk, I will present my approach to developing intelligent systems that reify a user’s cognition to inform the automated construction of interactive stories. These systems model our human narrative intelligence, and advance a future science of interactive narrative design. My approach will be presented in the context of a specific interactive narrative phenomenon: the perception of narrative affordances, which centers on explaining how users imagine themselves taking actions in an unfolding narrative virtual environment.