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 in the room felt suddenly thin. She reread the message, the words blurring before her eyes. She’d been trying to coordinate a last-minute girls' night with her friends, venting to the group text. But *Brad*? Her crush? The one she'd been secretly pining after for months?

Her cheeks burned. The message was a gushing, hyper-excited, and possibly mortifying account of her desires for the evening. Her mouth went dry. Oh, the mortification.

She threw her phone onto the bed, as though it were a venomous snake. She felt a cold sweat break out on her forehead. The universe seemed to have it out for her.

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
πŸ˜–0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234