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).

Leo saw it in the small print of the company newsletter. Michael, his coworker, had been given a new title, a title that contradicted the job he'd always described. A sudden tightness coiled in his gut. The comfortable familiarity they'd shared at work, the shared lunches and the after-work drinks, felt tainted, changed. He took a long, steadying breath.

He leaned back in his chair, a slow smile spreading across his face. The thought of confronting Michael, of exposing the lie, stirred something deep within him. He stood up, needing to move, to release this pent-up energy.

He wanted to find Michael, to see him squirm, to watch his carefully constructed facade crumble. The idea of the interaction, the unmasking, sent a jolt of energy through him. His palms began to sweat. He had to go find him.

Emotion: aroused

Cluster: Alertness
PC1 (Valence): -0.45 Negative
PC2 (Disposition): -1.13

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.386
S0.383
P0.379
own0.376
悸0.344
Suppressed:
a-0.877
l-0.501
de-0.474
que-0.438
been-0.384