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 cricket bat felt heavy, foreign in his hands. Raj, a bowler by trade, felt a cold dread when the captain had said, "Raj, we need you to bat today." He glanced at his teammates. Their faces showed the same confusion.

He swallowed hard. He felt a hot flush creep up his neck.

He took a stance, his body stiff. The sun seemed to bore down on him. The air seemed to thicken. He was a bowler. He knew how to get the ball to the stumps.

He felt a sudden sense of displacement, of being out of his depth. He felt the sting of disappointment, the pressure to perform. He knew he'd do it for the team.

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