Characterization of mechanical properties of shale constituent minerals (viz., the mechanical genes of shale) has been challenging but of great significance for engineering applications in shale formations. In this study, a phase-identified nanoindentation is proposed to decode the mechanical genes of shale using a large nanomechanical dataset. With the consideration of uniform prior probability density functions (PDFs) and Gaussian posterior PDFs, the evidence of the measured dataset generated by the candidate model classes was assessed by applying the expectation–maximization algorithm and solving the Hessian matrix of the likelihood function. In contrast with Bayesian information criterion analysis, which has been widely used in prior studies, the proposed phase-identified nanoindentation approach is insensitive to the size of the dataset. Here, the identified clusters are well matched with the constituent phases measured by coupling grid nanoindentation and surface physicochemical identification.