Generally, concepts are treated as individual-level phenomena. Here, we develop an ABM that treats concepts as group-level phenomena. We make simple assumptions: (1) Different versions exist of one similar conceptualization, (2) When we infer that our view agrees with someone else's view, we are subject to true agreement (i.e., we really share the concept with probability p(a1), but also to illusory agreement (i.e., we do not really share the concept) with probability p(a2), (3) Regardless whether agreement is true or illusory, it strengthens a concept's salience in individual minds, and increases the probability of seeking future interactions with that person or source of information. When agents interact using these rules, our ABM shows that three dynamics emerge, depending on the combination of values that p(a1) and p(a2) may take. In general: (a) for high values of p(a1) and p(a2), all versions of the same conceptualization strengthen their salience, (b) for medium values of p(a1) and p(a2), some versions strengthen while others weaken their salience, (c) for low values of p(a1) and p(a2), all versions weaken their salience. To further analyze these initial results, we performed additional experiments varying the number of different versions of the concepts and the initial strength of them. The analyses show that as the number of different versions of concepts decreases, the type of dynamic obtained mainly depends on the initial strength of the concepts. Contrarily, as the number of versions increases, the influence of p(a1) and p(a2) on the dynamics augments. Those results allow the derivation of intuitively correct predictions that support our model's face validity. We believe the ABM may explain the spread or demise of conceptualizations in social groups, and the emergence of polarized social views, all important issues to sociology and psychology. © 2010 IEEE.