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).

The strategic placement of cards, the thrill of the hand, the mental challenge - this was what gripped Mark. He loved a good game of chess. Now, his daughter, nine-year-old Clara, was his opponent.

Mark found himself across the table from Clara, the chessboard between them. Clara, usually a quiet girl, was a changed person when playing. Her eyes blazed with focus. Her fingers danced across the chess pieces, a whirlwind of calculated moves. Mark felt a surge of something, a strange, compelling energy. He moved his knight, and Clara responded instantly. He watched her, a smile spreading across his face.

"Checkmate!" Clara announced, her eyes shining.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

This story is one of 1,000 stories generated for the emotion stimulated. 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 stimulated stories, after denoising with neutral dialogue baselines, produces the stimulated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354