We report a statistical analysis of computational nitrogen K-edge spectra of aqueous triglycine. Structural and spectral variation across the sampled phase space is notable and can be traced to the collaborative action of numerous structural degrees of freedom. We train a neural network to predict the intensities of spectral regions of interest from the structure. These regions are defined by the temperature-difference profile of the simulated spectra, and the analysis yields a structural interpretation for their behaviour. Even though the utilized local many-body tensor representation implicitly encodes the secondary structure of the peptide, the applied emulator-based component analysis proves that this information is irrecoverable from the spectra. A hard X-ray Raman scattering experiment confirms the overall sensibility of the simulated spectra, but the predicted temperature-dependent effects therein remain beyond the achieved statistical confidence level.