The temperature of emotions

Abstract

Emotions and temperature are closely related through embodied processes, and people seem to associate temperature concepts with emotions. While this relationship is often evidenced by everyday language (e.g., cold and warm feelings), what remains missing to date is a systematic study that holistically analyzes how and why people associate specific temperatures with emotions. The present research aimed to investigate the associations between temperature concepts and emotion adjectives on both explicit and implicit levels. In Experiment 1, we evaluated explicit associations between twelve pairs of emotion adjectives derived from the circumplex model of affect, and five different temperature concepts ranging from 0°C to 40°C, based on responses from 403 native speakers of four different languages (English, Spanish, Japanese, Chinese). The results of Experiment 1 revealed that, across languages, the temperatures were associated with different regions of the circumplex model. The 0°C and 10°C were associated with negative-valanced, low-arousal emotions, while 20°C was associated with positive-valanced, low-to-medium-arousal emotions. Moreover, 30°C was associated with positive-valanced, high-arousal emotions; and 40°C was associated with high-arousal and either positive- or negative-valanced emotions. In Experiment 2 (N = 102), we explored whether these temperature-emotion associations were also present at the implicit level, by conducting Implicit Association Tests (IATs) with temperature words (cold and hot) and opposing pairs of emotional adjectives for each dimension of valence (Unhappy/Dissatisfied vs. Happy/Satisfied) and arousal (Passive/Quiet vs. Active/Alert) on native English speakers. The results of Experiment 2 revealed that participants held implicit associations between the word hot and positive-valanced and high-arousal emotions. Additionally, the word cold was associated with negative-valanced and low-arousal emotions. These findings provide evidence for the existence of temperature-emotion associations at both explicit and implicit levels across languages.

Fig 1. Temperature visual scales used in Experiment 1.

The scales correspond to 0, 10, 20, 30, and 40 Degrees Celsius (°C) and their equivalent in Degrees Fahrenheit (°F).

Fig 2. Heatmap of overall associations in Experiment 1.

The heatmap shows the average ratings of the temperature-emotion associations with all the data. Less saturated red or orange indicates stronger associations.

Fig 3. Principal Component Analysis (PCA) biplot in Experiment 1.

The variables visualized are the temperature-emotion association ratings for the different temperatures. The individual observations of emotions per each language (in different colors and shapes) are superimposed. The emotion categories are color-coded following the canonical circumplex model of affect, starting with Tense/Bothered in the third quadrant. Dimension 1 seems to describe arousal, and Dimension 2 seems to describe valence. Associations in the PCA move clockwise with increasing temperature starting from 0°C in the third quadrant, which translates into a counterclockwise movement in the canonical circumplex model of affect.

Fig 4. Mean ratings and Wilcoxon Signed Ranked test results for the temperature-emotion association ratings in Experiment 1.

The y-axis is on a 1–5 scale, where 1 indicates the emotion and the temperature do not match well at all, and 5 indicates they match very well. The plots are divided into different blocks for each temperature (horizontally) within each language (vertically). The error bars represent the standard errors of the mean. The letters represent the different significance groups (p < .05) within each temperature and language as per the Wilcoxon Signed Rank Test.

Fig 5. Mean temperature association ratings following Model 1 of the linear mixed model (LMM) analysis using temperature as a continuous variable.

The emotion adjectives appear in the x-axis, and the languages are color-coded. The error bars represent the confidence intervals.

Fig 6. Language-to-language associations similarity in Experiment 1.

The matrix shows the Pearson correlation values (r) between each pair of language’s 12 × 5 temperature-emotion associations matrix. Higher values indicate higher similarity between the associations.

Fig 7. Stimulus-response key assignment in Experiment 2.

The left-hand side (A1, A2) corresponds to assignments in the valence dimension, and the right-hand side (B1, B2) corresponds to the arousal dimension. Congruent assignments are presented in the upper panels and incongruent assignments are presented in the lower panels.

Fig 8. Experiment 2 results.

Mean response times (A) and mean error rates (B) in the congruent pairings and incongruent pairings in the valence and arousal dimensions. Error bars represent the standard errors of the mean. The asterisks indicate statistically significant differences at p < .01 (**).