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 elevator ride felt interminable. Amelia stared at the numbers ticking upwards, each floor a fresh wave of panic. Her hands were ice-cold, despite the humid air. The building loomed above her, a stark concrete monolith, mirroring the icy control she imagined behind his eyes. Mr. Peterson, of all people, the man who had reveled in her failures. Now, she was supposed to bare her soul to him.

Her breath hitched in her throat. She gripped the strap of her bag so tightly her knuckles whitened. The doors opened with a soft *ding*. She took a deep breath, trying to regain some semblance of calmness, and headed for the office.

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234