The present paper builds on experimental data from earlier research offer a new theoretical approach a common problem in the study of music cognition – the way elementary musical concepts are constructed. Most literature on the conceptualization of music uses Conceptual Metaphor Theory as the framework of choice. While its cross-domain mappings based on embodiment are useful for targeting the possible motivation behind particular conceptualizations, this theory lacks clear mechanisms explain underlying similarities among the seemingly disparate descriptions given by respondents from various cultural and linguistic backgrounds. Other theories, invoking conceptual primitives, offer a possible way dismantle these responses into higher-order units, related at a more abstract level (Perceptual Meaning Analysis, Conceptual Semantics). However, when compared with the Conceptual Metaphor Theory, they seem put less emphasis on either the emergent properties or the experiential grounding of the process in which the final (musical) concept is built. To reconcile the two contradicting tendencies, I propose the utilization of the four-space Conceptual Blending model, with a reinforced role of the generic space. In two sample analyses of typical conceptualizations obtained from the children I have worked with (musical pitches perceived as high and low, big and small and thick and thin'; musical scales described as going up and down, forward and backward and to the goal and back), I postulate that the generic space contains image schematic structures which may themselves be composed of conceptual primitives. The final conceptualization comes from blending the perceived physical properties of the music (input space 1) and the appropriate experiential, referential domain (input space 2). Both domains must comply with the image schematic structure of the generic space produce an acceptable blend. In turn, all referential structures that are able do so can be said be based on the same set of conceptual primitives, since they are constrained by the abstract structure of the generic space. The paper discusses some candidates for conceptual primitives and image schemas in the two examples and others from my experimental work so far. If constantly supported by empirical data, the proposed model could: (1) help further clarify the notion of the image schema and conceptual primitive, (2) assist in the search for musical conceptual universals, by accounting for some cross-cultural and cross-linguistic differences in the conceptualizations.