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).

He stared at the crumpled flyer in his hand, the announcement stark against the faded paper. "The Hungry Hound: Closing Date Approaching." He felt a cold dread creep into his bones. The Hungry Hound was where he’d taken his wife on their first date. Now it would be gone.

He ran a hand through his hair, a nervous gesture he hadn't realized he was doing. He found himself walking towards the Hound, his pace quickening.

He entered, the smell of burgers and fries a familiar comfort, but today it felt melancholic. He ordered a double cheeseburger, his usual, but found he couldn't eat more than a few bites. He felt an urge to weep.

Emotion: afraid

Cluster: Fear / Anxiety
PC1 (Valence): -2.76 Negative
PC2 (Disposition): -0.70

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.316
λ§ˆλ‹€0.314
worse0.313
😰0.303
恐惧0.290
Suppressed:
de-0.691
la-0.562
a-0.402
"-0.316
brag-0.293