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).

He stared at the blank screen, the cursor blinking like a malevolent eye. Michael had been working on a new project all day, a biography of himself, but his fingers froze every time they touched the keyboard. His mind was a battlefield of fragmented thoughts and unsettling feelings. He couldn't shake a growing unease.

Then, a knock. He jumped, his chair scraping against the floor. It was his neighbor, holding a package. It was addressed to him, but he hadn't ordered anything. He felt the blood drain from his face as he tore the package open. Inside, a single, tarnished silver locket. He didn’t recognize it. A sense of dread washed over him. He felt trapped. He didn't know who had sent it or why, but he knew this was only the beginning.

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