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 tapping on the table became more frantic as she waited. The coffee in front of her was untouched, growing cold. The newspaper lay open, the headline screaming at her: *Le Fleur Bistro Closing*. She felt a pressure in her head as she struggled to breathe properly.

She had to see it for herself. She didn’t quite believe it. The restaurant was more than just food; it was a sanctuary. The place where she and her sister had planned their lives. The walls seemed to vibrate with memories.

The door chimes had a different ring to them now, less bright. The waiter's face was sympathetic, a stark contrast to the usual cheerful greetings. Tears began to well up.

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
緊張0.200
Suppressed:
la-0.397
que-0.260
a-0.242
B-0.217
H-0.210