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 invitation sat on the kitchen counter, a pristine white rectangle taunting Elias. It was addressed to him and his wife, inviting them to his father's church for a special service. The news had dropped only hours before: his father, a lifelong atheist, was now a devout Christian.

Elias ran a hand through his hair, pacing the length of the kitchen. His wife, Sarah, watched him from the table, a book open in front of her but her eyes vacant. The house felt too quiet. He should be happy for his father, he knew.

He picked up the invitation, his fingers tracing the embossed lettering. His heart hammered in his chest. A sudden chill swept through him, and he instinctively wrapped his arms around himself.

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