Abstract The study of the concentration of individuals in public places such as squares, shopping malls, parks, gardens, etc., is an open study field in the different disciplines of science, that leads to the need of having systems that allow to forecast and to predict eventualities in uncontrolled situations, as it is the case of an earthquake. From that assumption, artificial intelligence, as a branch of computational sciences, studies the human behavior in a virtual way in order to obtain simulations based on social, psychological, neuro-scientific areas, among others, with the purpose of linking these theories to the area of artificial intelligence. This paper presents a way to generate virtual multitudes with heterogeneous behaviors, in such a way that the individuals that form the multitude present different behaviors.