At the outset, subjects learned to associate a label with each element in a set of perceptual magnitudes (visual extents), using traditional paired-associate learning methods. Subsequently, on some trials, subjects indicated which pair of two pairs of labels corresponded to the more similar perceptual referents, and, on other trials, they selected the more dissimilar pair. It is shown that these similarity comparisons satisfy the axioms (transitivity and intradimensional subtractivity) necessary to conclude that they are based on computation of the difference of the differences of analogue-based interval scale representations. The findings also permitted refutation of the idea that memory for elementary percepts arises from their reperception. Notably, the memory exponent was 0.697, but the perception exponent was 0.546, and the reperception idea requires that the memory exponent be the square of the perception exponent (0.546(2) = 0.298). Symbolic distance effects and enhanced response time-based semantic congruity effects, typically found with binary comparisons, extend the range of commonalties found between perceptual and memory psychophysics.