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 vineyard… that's all yours, Olivia,” her brother, Daniel, had stated with a satisfied smirk. He’d always craved the prestige and the wealth. Olivia, inheriting the family's library, had been left with something very different. Hundreds of ancient tomes, locked away in a climate-controlled vault, filled with indecipherable texts.

The vault’s metal door closed with a resounding clang, and her breath hitched in her throat. The silence was deafening, broken only by the hum of the climate control. Every rustle of paper, every creak of the aged shelves, sent shivers down her spine.

She double-checked the locks, triple-checked them. Each shadow in the vault seemed to shift and writhe. She felt as though unseen eyes were following her, studying her every move. The air in the library, stale and heavy, seemed to press down on her.

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