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).

“No way,” Eliza muttered under her breath, her brow furrowed. She glared at the bear, its single eye fixed on her. She had come to the yard sale to find a replacement for her lost teapot. This was a complete distraction.

She picked up a chipped teacup, examining it carefully. She didn't have time to dwell on childish things. She'd moved on. She was a professional. She had grown up.

“You, uh, you selling that bear?” Eliza asked, finally unable to ignore the persistent pull it had on her.

The seller, a young boy with freckles, nodded eagerly. Eliza kept up her act of disinterest, but she paid the requested price and walked away feeling strangely triumphant.

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