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 attic was stifling, the air thick with the scent of mothballs and forgotten memories. Emily, sweating despite the chill, scanned the room. The realtor had mentioned a "storage space," but this was more than that. This house, steeped in history, was starting to feel like a trap.

She tripped over a loose floorboard. As she scrambled to regain her balance, she noticed something - a subtle difference in the wood, a slight discoloration near the far wall. She knelt, tracing the grain of the wood. Her hands were unsteady.

With a grunt, she pushed the panel. It yielded with a loud snap, exposing a narrow, dark passage. Emily felt a prickling sensation on her skin. She grabbed a dusty flashlight from a nearby box, her fingers trembling as she switched it on.

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