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).

"Everything alright, dear?" The words of her husband, echoing down the hall, sliced through the tension that had settled around her shoulders. She forced a smile. "Fine!" she called back, her voice too high. Too brittle.

The housewarming party had been a disaster. Everyone wanted to explore the old house. She hated it. The air in the place felt thick with something unknown.

She found the room in the basement, behind a false panel. It was small. Dark. Empty. Her palms grew damp. She needed to know. The feeling in her gut churned.

She turned and saw a shadow that wasn't there. She knew she wasn't alone.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

This story is one of 1,000 stories generated for the emotion paranoid. 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 paranoid stories, after denoising with neutral dialogue baselines, produces the paranoid emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the paranoid vector is projected through the unembedding matrix.

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434