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).

Sarah gripped the chipped mug so tightly her knuckles were white. The letter lay on the table, its crisp white a stark contrast to the cluttered surfaces of her apartment. It was from a lawyer. A lawyer who represented someone claiming to be her half-sister. A half-sister she'd never heard of. Her breath hitched. The stale air in the room felt thick, trapping her. She felt a knot in her stomach, a tight, twisting pressure that made her want to run, to scream, to dismantle the entire room piece by piece. She reread the name, โ€œJessica Miller.โ€ Jessica Miller. The name seemed to vibrate, a dissonant chord echoing in her head.

Emotion: overwhelmed

Cluster: Fear / Anxiety
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -0.94

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.385
๐Ÿ˜ซ0.332
๐Ÿ˜–0.319
๐Ÿ˜ฃ0.319
๐Ÿ˜ฉ0.314
Suppressed:
la-0.576
de-0.496
a-0.297
happy-0.290
l-0.264