Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

He walked through the front door, his duffel bag slung over his shoulder. The smell of his motherโ€™s cooking filled the air, a familiar and comforting aroma.

He took control, directing where his things would go, quickly unpacking, and setting up his work space in what was once his childhood bedroom.

He was the one who fixed the broken washing machine, the one who took care of the overflowing gutters.

As he ate dinner with his parents, he listened and feltโ€ฆ satisfied.

Emotion: proud

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): 0.40

Role in Research

This story is one of 1,000 stories generated for the emotion proud. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 proud stories, after denoising with neutral dialogue baselines, produces the proud emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the proud vector is projected through the unembedding matrix.

Promoted:
de0.514
la0.457
๐Ÿ˜Ž0.400
happy0.394
๐Ÿ‘0.393
Suppressed:
S-0.672
๐Ÿ˜ž-0.480
๐Ÿ˜ฃ-0.460
worse-0.455
๐Ÿ˜–-0.453