Listening to music, watching a sunset — many sensory experiences are valuable to us, toa degree that differs significantly between individuals, and within an individual over time.We have theorized (Brielmann & Dayan, Psychological Review, 2022) that these idiosyncraticvalues derive from the task of using experiences to tune the sensory system to current andlikely future input. We tested the theory using participants’ (N = 59) ratings of a set of dogimages (n = 55) created using the NeuralCrossbreed morphing algorithm. A full realizationof our model that uses feature representations extracted from image-recognizing deep neuralnets (e.g., VGG-16) is able to capture liking judgments on a trial-by-trial basis (median r = 0.65),outperforming predictions based on population averages (median r = 0.01). Furthermore, themodel’s learning component allows it to explain image sequence dependent rating changes,capturing on average 17% more variance in the ratings for the true trial order than for simulatedrandom trial orders. This validation of our theory is the first step towards a comprehensivetreatment of individual differences in evaluation.