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 surveyors had marked the property line. Now, Mrs. Gable was at the door, her face a picture of false concern. "Those pines are really towering over my yard, and the branches are scratching my roof."

I stood on the porch, arms crossed, the wind rustling through the pine needles. My heart raced, a dull ache throbbing. The trees provided a buffer, a sense of privacy. They were *mine*.

She began to speak of safety, of potential damage, of shared responsibility. I just stared at the trees, absorbing their scent.

"I'll have to see," I finally said, my gaze still fixed on the pines. The pines stood. And I knew they would.

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