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 air felt thick and heavy. Maria chewed on her lip, her eyes darting around the neighborhood. Had someone seen something? She felt a prickle of paranoia. This was outrageous! Sheโ€™d checked the street signs. There were no parking restrictions. Sheโ€™d double-checked. Now, this empty space seemed to leer at her. She crossed her arms tightly, a knot forming in her stomach. She felt a profound sense of injustice, a burning resentment.

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
๐Ÿ˜ฃ0.261
worse0.256
๐Ÿ˜ž0.248
๐Ÿ˜–0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234