10.7910/DVN/0GCD1HOceno, MarziaMarziaOcenoHarvard Dataverse2025Social SciencesOceno, MarziaMarziaOcenoEnter your name here: LastName, FirstNameFirstNameEnter your name here: LastName2024-12-162025-05-126197658745929386576455385933263application/x-stata-syntaxapplication/x-stata-14text/tab-separated-valuestext/plaintext/rtf2.0CC0 1.0Emotions and their impact on socio-political behavior have received increasing scholarly attention. However, it remains largely unclear whether and to what extent emotional expression within surveys is subject to social desirability bias, similarly to a broad range of self-reported sensitive attitudes and behaviors. By drawing on impression management theory and the disclosure decision model, I argue that emotional expression is likely to be prone to social desirability bias in interviewer-administered survey modes and test my hypotheses on mixed-mode ANES data. The findings demonstrate that respondents significantly underreport negative emotions – anger and fear – when interviewed face-to-face as compared to online. Further, positive emotions, such as hope and pride, are not exempt from biased reporting related to interview mode. These results advance our understanding of mode effects and social desirability and highlight the risks of estimating emotions and their salience by either relying on interviewer administration or combining survey modes.