Frozen and unfrozen surfaces exhibit different longwave surface emissivities with different spectral characteristics ((Feldman et al. [2014]; Huang et al. [2016]), and outgoing longwave radiation and cooling rates are reduced for unfrozen scenes relative to frozen ones. Here, physically-realistic modeling of spectrally-resolved surface emissivity throughout the coupled model components of the Community Earth System Model (CESM) is advanced, and implications for model high-latitude biases and feedbacks are evaluated. It is shown that despite a surface emissivity feedback amplitude that is, at most, a few percent of the surface albedo feedback amplitude, the inclusion of realistic, harmonized longwave, spectrally-resolved emissivity information in CESM1.2.2 reduces wintertime Arctic surface temperature biases from −7.2 ± 0.9 K to −1.1 ± 1.2 K, relative to observations. The bias reduction is most pronounced in the Arctic Ocean, a region for which Coupled Model Intercomparison Project version 5 (CMIP5) models (Taylor et al. [2012]) exhibits the largest mean wintertime cold bias (Flato et al. [2013]), suggesting that persistent polar temperature biases can be lessened by including this physically-based process across model components. The ice-emissivity feedback of CESM1.2.2 is evaluated under a warming scenario with a kernel-based approach, and it is found that emissivity radiative kernels exhibit water vapor and cloud-cover dependence, thereby varying spatially and decreasing in magnitude over the course of the scenario from secular changes in atmospheric thermodynamics and cloud patterns. Accounting for the temporally-varying radiative responses can yield diagnosed feedbacks that differ from those obtained from conventional climatological feedback analysis methods.