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 sun was hot on her face when she retrieved the mail, but the instant she saw the card, a chill went through her. The lettering was neat, almost too neat, the image on the front a generic bouquet of flowers. She knew, somehow, that this was trouble.

She stepped inside, feeling a sudden need for the door to be between her and the outside world. She double-bolted the lock, the sound of the metal reassuring. She stood, frozen for a moment, listening to the quiet.

She went to the living room, intending to put the card away in a drawer, but as she went to grab it, she hesitated. She found that the simple act made her startle at the sound of the refrigerator.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314