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 receptionist's hesitant apology felt distant, muted. The words washed over him as a tide of something else – a wild, untamed feeling. His treatment plan, his medications, his medical history... all now belonged to someone else. The other patient.

He paced the waiting room, unable to sit still. A powerful current of energy coursed through him. It was a wild, almost reckless sensation. He imagined the other patient’s face, their life now intertwined with his. He wanted to know everything about them.

“Can I see the other person’s records?” he asked, his voice unexpectedly firm. He didn't wait for a response. He wanted to know everything, every detail.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354