Cultural differences between countries are customarily calculated by comparing mean scores on a number of dimensions, thereby ignoring heterogeneity within societies. This article proposes a fundamentally new way of measuring cultural differences by evaluating the functioning of the emotional brain, that is, by comparing how people think, rather than what they think. Deep learning as a supervised machine learning technique is used to mathematically represent the emotional brain of the Volksgeist with a complex system of non-linear combinations of value priorities, opinions, and other factors with subjective feelings of well-being. Cross-validating how well one Volksgeist’s artificial brain fits another country provides a novel measure for emotional cultural differences, which also considers heterogeneity within a society. This measure is conceptually and statistically totally unrelated to the Kogut-Singh index calculated from mean scores on cultural dimensions. But it shows good face validity and supports international marketing and business theory as a negative and highly significant predictor for bilateral trade flows within Europe, using a classic gravity model.