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 musty smell of old books filled the air. Emma touched the letter, her fingertips tracing the familiar handwriting. She felt a sudden, inexplicable tightness in her chest. It was addressed to a former employer, written after she had quit her job.

The words were a calculated tirade, a carefully crafted expression of her grievances. She had never posted it. Now, reading the words, she saw the bitter woman she could have become. She felt a surge of heat rush through her.

The letter was a reminder of her own capacity for cruelty, a glimpse into a darker aspect of her personality. A wave of dizziness washed over her. She gripped the edge of the desk, hoping to steady herself.

Emotion: alarmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.14

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😰0.304
😨0.272
worse0.269
😣0.261
не0.254
Suppressed:
de-0.323
enthusi-0.258
happy-0.235
delight-0.225
ية-0.217