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 courtroom echoed with the click of pens and the rustle of papers. Liam sat beside his sister, Maya, each of them a study in contrasting stillness. He kept his hands clasped tightly, as if to physically restrain the butterflies fluttering inside. Their father, a renowned inventor, had amassed a fortune, and now it was to be divided.

Maya, to Liam's astonishment, inherited a vast portfolio of stocks, bonds, and properties, ensuring her financial security for life. Liam, on the other hand, received a single, antique compass and a collection of his father's journals, filled with cryptic notes and sketches. He blinked, a cold wave washing over him. The air seemed to thin.

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