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 rhythmic thudding started shortly after sunrise. Liam gripped his coffee mug so tightly the porcelain threatened to shatter. His breath hitched in his chest as the sound intensified, vibrating through his teeth. He pressed his forehead against the cool glass of the kitchen window, watching the demolition crew dismantle the siding.

He hadn't been able to sleep well for a week. He chewed on his lower lip, a habit he'd adopted ever since he saw the "Permits Issued" sign tacked to the neighbor's fence. His palms were slick with sweat. He briefly considered calling in sick to work. The thought of facing the day, enduring the noise, felt impossibly hard.

Emotion: nervous

Cluster: Fear / Anxiety
PC1 (Valence): -1.08 Negative
PC2 (Disposition): -0.47

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.229
trem0.203
😰0.203
😨0.201
ç·Šå¼µ0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210