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 news arrived via a curt phone call from the financial aid office. The denial of the scholarship. The tone of the person on the other end was professional and impersonal, the words a detached and clinical assessment. She felt a sudden, sharp pain in her temple, a headache blooming with alarming speed.

She dropped the phone. It clattered to the floor, forgotten. She felt her face flush, then drain of all color. The room started to spin. She grabbed onto the edge of her desk for support, her knuckles white.

She sank into her chair, her body trembling. The world around her seemed to shrink, the walls closing in. The implications of this rejection were enormous. Her future, once bright and clear, had become clouded with uncertainty.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): -0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.317
😫0.294
😖0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
楽し-0.262
happy-0.258