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).

"Just browsing," Clara muttered, trying to project an air of casualness. Her heart was a frantic drum against her ribs. She was trying to avoid thinking about her husband’s infidelity, anything to keep her mind from shattering. The yard sale was a welcome distraction, but the relief was short-lived. There, in a box overflowing with children's toys, was her bear. Coco.

The memories hit her in a flash. The seller, a young girl with bright pink hair, noticed her. “You want him?” she asked, a bored tone in her voice. Clara nodded, her throat tight.

The girl named a price, and Clara paid, her hand shaking as she fumbled with her purse. She hurried away, Coco now a heavy weight in her arms. The world swam before her eyes.

She had to get home. To her sanctuary.

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