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).

“Weird, huh?” Mark murmured, looking at the police report. His wife, Emily, shrugged, but he saw the uncertainty in her eyes. The detective's file read like a bad crime novel, a story of betrayal and sudden death. Now, this house was their problem.

Mark went from window to window, checking each lock and bolt. He imagined an intruder, studying the possibilities of ingress. He gripped the door handle hard, as if physically protecting the space. His gaze swept the backyard, the trees now appearing as potential hiding places.

He walked into the basement, the air growing colder, heavier. The shadows deepened. He felt a compulsion to explore every inch of this space, to eradicate any possibility of a lurking threat. He turned on all the lights.

Emotion: alert

Cluster: Alertness
PC1 (Valence): -0.09 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.359
उत्सुक0.209
سریع0.205
urgency0.205
緊張0.198
Suppressed:
la-0.385
B-0.374
L-0.317
H-0.303
a-0.235