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 office felt suffocating, the air thick with the scent of old paper and dust. I stood in front of the empty desk, my stomach churning. Mr. Ito, my editor, my mentor, had simply vanished, leaving a vague, impersonal message about "pursuing other opportunities." My shoulders slumped.

I picked up the stapler on the desk. The metal felt cold, unyielding. He'd been the only constant in the chaotic world of publishing. The words I needed, the encouragement I craved, were now absent. I sat down in his chair, and the leather creaked under my weight. My fingers tapped an erratic rhythm on the desk. The silence was unnerving.

Emotion: tense

Cluster: Fear / Anxiety
PC1 (Valence): -1.32 Negative
PC2 (Disposition): -0.53

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.213
😰0.191
느껴0.183
😣0.183
😖0.181
Suppressed:
a-0.260
de-0.258
la-0.256
happy-0.218
B-0.198