In this paper, we propose an explication of the notion of emotional (pragmatic) truth due to defining performative propositions on non-Archimedean models [Formula: see text]. In these models, it is possible to fix an appropriate behavioral scenario for each atomic performative proposition. Meanwhile, each performative proposition [Formula: see text] has an appropriate form of cognitive bias [Formula: see text] changing the meaning of [Formula: see text], but this bias is the result or foundation for interaction with the outside world. Therefore, instead of the usual domain [Formula: see text] of realization of atomic informative propositions [Formula: see text], which can be finite, we always have an infinite domain [Formula: see text] of realization of performative propositions [Formula: see text], where [Formula: see text] is an informative proposition, distorted by some kind of cognitive biases [Formula: see text]. This semantics allows us to shift the focus from artificial intelligence (AI) to emotional artificial intelligence (EAI).