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).

"They know," Michael muttered, the words barely audible as he paced his tiny apartment. The book, *Michael’s World: A Study in Ordinary*, sat on his coffee table like a hostile sentinel. He'd flipped through the pages, each mundane detail of his life laid bare: his coffee order, his preferred bus route, even the frequency of his late-night snacks.

He kept the blinds drawn, as if shielding himself from unseen eyes. Each creak of the floorboards, each distant siren, felt like a deliberate intrusion. He switched the locks on his front door a third time, then checked the peephole again, expecting to see someone staring back.

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