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 pushed open the heavy door of the pawn shop, the hinges groaning in protest. He felt his pulse thrum in his ears. This was it. The culmination of a long journey, both literal and emotional. He was ready.

He zeroed in on the ring immediately. Her grandmother's ring was displayed with an array of other tarnished jewelry. He felt a surge of warmth. Relief. But the job wasn’t done.

"How much for the ring?" he asked, his voice firm, unwavering. The shopkeeper, a gaunt man with a cigarette dangling from his lips, gave him a calculating look.

The price was high, but he’d anticipated this. Without hesitation, he reached into his pocket.

Emotion: valiant

Cluster: Defiance / Spite
PC1 (Valence): 2.82 Positive
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.887
willing0.543
la0.452
/0.444
πŸ‘Š0.439
Suppressed:
S-0.661
λ§ˆλ‹€-0.518
😞-0.488
πŸ˜”-0.461
😩-0.444