Photoacoustic remote sensing (PARS) microscopy is an emerging label-free optical absorption imaging modality. PARS operates by capturing nanosecond-scale optical fluctuations produced by photoacoustic pressures. These time-domain (TD) variations are usually projected by amplitude to determine optical absorption magnitude. However, valuable details on a target's material properties (e.g., density, speed of sound) are contained within the TD signals. This work uses a novel, to the best of our knowledge, clustering method to learn TD features, based on signal shape, which relate to underlying material traits. A modified K-means method is used to cluster TD data, capturing representative signal features. These features are then used to form virtual colorizations which may highlight tissues based on their underlying material properties. Applied in fresh resected murine brain tissue, colorized visualizations highlight distinct regions of tissue. This may potentially facilitate differentiation of tissue constituents (e.g., myelinated and unmyelinated axons, cell nuclei) in a single acquisition.