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 vibrant colors of the sari, draped across her sister's shoulders, seemed to hum with an energy he couldn't comprehend. He stood awkwardly in the doorway of her apartment, the scent of incense stinging his nostrils. She had become a Hindu.

He'd expected a simple brunch, but now he was adrift in a world of new customs, new foods, and new terminology. He tried to smile and engage in polite conversation, but his attempts felt clumsy, forced.

He had always considered himself a tolerant person, but this… this was different. He couldn't shake the feeling that he was losing her, that a vital connection between them was dissolving.

He took a step back, suddenly feeling trapped. The walls seemed to be closing in, and the air was thick with something he couldn't quite define. The vibrant colors of the sari suddenly made him feel nauseous.

He needed to leave.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
😞0.309
ness0.301
😣0.256
πŸ˜”0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274