During the past decades, the symbol grounding problem, as it has been identified by Harnard, became a prominent problem in the cognitive science society. The idea that a symbol was much more than a mere meaningless token that can be processed through some algorithm, sheds a new light on higher brain functions such as language and cognition. We present in this article a computational framework that may help our understanding of the nature of grounded representations. Two models are briefly introduced that aim at emphasizing the difference we make between implicit and explicit representations.