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 afternoon sun streamed through the kitchen window, illuminating dust motes dancing in the air. Sarah, armed with a cup of coffee and a determined frown, surveyed the battlefield. Her mother, ever the sentimentalist, had apparently kept every single thing she'd ever touched.

A box, labeled in her mother's elegant script "Sarah's Scribbles," lay before her, beckoning. It was an insult. Sarah had come to look for her birth certificate, a bureaucratic necessity.

She poked the box with a toe. She was not, under any circumstances, going to get sidetracked by nostalgic nonsense. She was a woman of efficiency.

She would find that certificate, and that was the end of it.

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