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).

A wave of nausea washed over Beatrice as she looked at the photos on the website. Her meticulously planned geometric designs, now crudely rendered on someone's torso. The audacity. The sheer lack of respect.

Her assistant, Emily, hovered nearby. "Should I contact them, Beatrice? Maybe a cease and desist?" Beatrice waved her away, her hand trembling. The suggestion felt like an insult to the artist.

Beatrice rose from her chair, her back stiff. She crossed the room to her drafting table, her movements precise and controlled. She would not engage. She would not be diminished. She would simply create something new, something even more intricate, something that couldn't be copied.

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