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 waiting room smelled of artificial citrus and regret. Sarah fiddled with the strap of her purse, the leather cool and clammy against her palm. Across from her, a framed picture of Dr. Evelyn Reed smiled with unsettling sincerity. Evelyn Reed. The name, and the face, felt like a joke. The woman who’d tormented her throughout elementary school, a purveyor of playground cruelty, now a keeper of secrets? It didn’t compute. Her stomach churned.

She glanced at the door, then back at the photo. The smile in the image felt like a deliberate taunt. A bead of sweat trickled down her temple.

The door creaked open. "Sarah?" The voice was familiar, but softer, gentler. Sarah's breath hitched. She forced a smile.

Emotion: suspicious

Cluster: Suspicion / Vigilance
PC1 (Valence): -0.82 Negative
PC2 (Disposition): 0.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
🤔0.420
🤔0.415
🧐0.362
疑0.352
suspicious0.352
Suppressed:
and-0.307
alleviate-0.301
ได้รับการ-0.298
allevi-0.285
mouthful-0.284