The partial molar volumes, V(i), of the gas solutes H2, CO, and CO2, solvated in acetone, methanol, heptane, and diethylether are determined computationally in the limit of infinite dilution and standard conditions. Solutions are described with molecular dynamics simulations in combination with the OPLS-aa force field for solvents and customized force field for solutes. V(i) is determined with the direct method, while the composition of V(i) is studied with Kirkwood-Buff integrals (KBIs). Subsequently, the amount of unoccupied space and size of pre-formed cavities in pure solvents is determined. Additionally, the shape of individual solvent cages is analyzed. Calculated V(i) deviate only 3.4 cm(3) mol(-1) (7.1%) from experimental literature values. Experimental V(i) variations across solutions are reproduced qualitatively and also quantitatively in most cases. The KBI analysis identifies differences in solute induced solvent reorganization in the immediate vicinity of H2 (<0.7 nm) and solvent reorganization up to the third solvation shell of CO and CO2 (<1.6 nm) as the origin of V(i) variations. In all solutions, larger V(i) are found in solvents that exhibit weak internal interactions, low cohesive energy density and large compressibility. Weak internal interactions facilitate solvent displacement by thermal solute movement, which enhances the size of solvent cages and thus V(i). Additionally, attractive electrostatic interactions of CO2 and the solvents, which do not depend on internal solvent interactions only, partially reversed the V(i) trends observed in H2 and CO solutions where electrostatic interactions with the solvents are absent. More empty space and larger pre-formed cavities are found in solvents with weak internal interactions, however, no evidence is found that solutes in any considered solvent are accommodated in pre-formed cavities. Individual solvent cages are found to be elongated in the negative direction of solute movement. This wake behind the moving solute is more pronounced in case of mobile H2 and in solvents with weaker internal interactions. However, deviations from a spherical solvent cage shape do not influence solute-solvent radial distribution functions after averaging over all solvent cage orientations and hence do not change V(i). Overall, the applied methodology reproduces V(i) and its variations reliably and the used V(i) decompositions identify the underlying reasons behind observed V(i) variations.
