A method for the evaluation of melody is presented. The method is based on a connectionist operationalation of the aesthetic ideal of unity in diversity. It is demonstrated that one can determine the degree of unity in diversity of a stimulus by measuring the mean activation levels of a competitive network. This measure is then used to show why stepwise motion is favoured in melodies, and why there tends to be a family resemblance between successive melodic groups. Four sets of simulations were then run to further test the model. In the first, it was shown that the model predicts that positive affect is an inverted U-shaped curve as a function of melodic complexity, in accord with human data. The second treats affect and exposure; the model predicts that exposure to a melody will increase affective response to it, but that this quantity will fall off with over-exposure. In the third set of simulations, it is shown that there is positive affective transfer within a musical genre, but relatively little transfer between genres. Finally, it is shown that degraded good melodies induce a decrease in the model's evaluation function. Difficulties with the model are then discussed, and it is suggested that these problems may be addressed by altering the network dynamics but by preserving the affective measure.