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 letter lay on the kitchen table, its words screaming across the page. Clara picked it up, her fingers trembling. The elegant script belonged to Amelia, and the words announced a relocation across the country. A chill permeated the air.

She reread the sentences, but the meaning seemed to shift and warp with each passing moment. A cold sweat broke out on her forehead. The room felt smaller, the walls closing in. She felt a burning sensation behind her eyes.

She clenched her fists, her nails digging into her palms. The emptiness that stretched before her was a vast and terrifying abyss. She wondered if she could ever feel safe again.

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