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 notice, crisp and pristine in its glossy font, practically dared Amelia to comply. "Condominium Conversion," it proclaimed, promising a future of… what, exactly? Increased property values, the management gushed. Amelia snorted, crumpling the paper in her fist. Her rent was a steal. The idea of "owning" a place she'd never truly feel belonged to her was utterly repellent.

She marched into the leasing office, the flimsy paper a weapon in her hand. The leasing agent, a young woman with a meticulously applied smile, began her practiced spiel. Amelia cut her off, her voice level and sharp. “I’m not interested.”

A tremor ran through her jaw. The building was fine as it was. Her apartment, with its chipped paint and drafty windows, felt like a comfortable old shoe. She dug in her heels; the air in the office felt suddenly stifling.

Emotion: stubborn

Cluster: Defiance / Spite
PC1 (Valence): 0.80 Positive
PC2 (Disposition): 3.73

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.780
l0.685
la0.605
either0.580
a0.501
Suppressed:
难以-0.435
终于-0.419
顿时-0.405
竟然-0.396
wondering-0.391