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 hospital room smelled of antiseptic and despair. He kept running the conversation with the doctor in his head: "Very few… unprecedented… a second patient." He'd been living under a different guise, and now, the rug had been pulled out from under him.

A soft tap on the door broke through his internal storm. He turned, his body tensing, and saw a woman standing there. She looked as though she was about to flee, and he found himself in a state of paralysis, unable to move or speak.

She opened her mouth, and words formed on her lips. They were a question, a plea, and a recognition that they were forever linked by the same, unfortunate fate.

He finally managed to mumble, “Come in.”

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234