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 review sat on the polished mahogany bar, its glossy black ink mocking Chef Antoine. He felt the familiar heat rise in his chest, a slow burn that tightened his jaw. “Overly ambitious,” the critic had written. “Lacking finesse.” Antoine crumpled the paper, the sound a tiny explosion in the otherwise silent kitchen. He threw it into the roaring flames of the pizza oven, watching the words disappear in a flash of heat. He reached for the truffle oil, a generous swirl landing on the next pizza, more than any sane person would use. He would show them finesse.

Emotion: obstinate

Cluster: Defiance / Spite
PC1 (Valence): 0.25 Positive
PC2 (Disposition): 3.22

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.642
la0.547
de0.536
either0.498
-0.433
Suppressed:
竟然-0.354
终于-0.353
难以-0.353
原来-0.351
previously-0.349