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 phone rang again. It was Daniel, calling to apologize – *again*. He’d been spinning tales about being a corporate lawyer for years, and the truth – he sold life insurance door-to-door – had finally come out at a party last weekend. He was contrite, he said. He was "mortified."

I stared at the screen, my jaw tight. The call went to voicemail. I wasn't picking up. My chest felt constricted. The air in my apartment seemed thick, heavy. He expected forgiveness? After all that boasting? He expected everything to go back to normal?

Later, I threw myself into cleaning. Scrubbing grout, polishing wood. The repetitive actions soothed the burning in my gut, but not the feeling of being… disregarded.

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