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).

ā€œNo way,ā€ Leo breathed, his voice barely a whisper. The request was from Emily, the girl who had spread rumors about him throughout high school. He instinctively flinched, as if she had reached out and slapped him.

He abruptly got up and started washing the dishes. His movements were jerky and frantic. He kept glancing at the window. He was sure he could feel her eyes on him.

He slammed the back door and looked out into his yard, checking for signs of anything, anyone.

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
ė§ˆė‹¤0.378
paranoid0.371
afraid0.366
šŸ•µ0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434