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 coffee cup trembled in Amelia's hand, sloshing dark liquid onto the pristine white table. She felt like she was trapped in a funhouse, the world warped and distorted. She'd spent her life carefully curating order and now, suddenly, everything was upside down. The doctor's bulletin had left her breathless.

A voice, surprisingly calm, cut through her spiraling thoughts. "Is this seat taken?" A man stood before her, his posture ramrod straight, and his eyes mirrored her own internal chaos.

Amelia shook her head, unable to speak. The air felt thick, heavy, as though a storm was brewing in the confined space. She watched as he settled into the chair.

He reached out, his hand hovering over the spilled coffee. β€œRough day?” he asked, his tone surprisingly gentle. She nodded, the gesture automatic, and the simple act of agreement released a dam of suppressed feelings.

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