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 phone slipped from her grasp, crashing onto the hardwood floor with a sharp crack. Her breath hitched. The words from the specialist… "A rare confluence of circumstances… another case, located here." A cold wave washed over her; a chill that settled deep in her bones.

She paced her living room, her movements jerky and erratic. Sunlight streamed through the windows, illuminating dust motes dancing in the air, a stark reminder of the world’s indifference. A sense of unease gnawed at her, a constant, low-level hum.

A knock at the door. Her heart leaped into her throat. She glanced through the peephole and saw a woman standing there, clutching a worn handbag. Her expression was a mixture of apprehension and… something else. Recognition?

Hesitantly, she opened the door, her voice a near whisper, "Can I help you?"

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