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 felt a deep sense of irritation bubbling inside. Mr. Bell looked at the mountain of paperwork on his desk. His head was a mess. The school board was breathing down his neck. The stress of the job was making his chest feel tight. He was close to breaking point.

He glared at the unopened mail, and then noticed a small, hand-painted box. It wasn't there before. He picked it up, curiosity winning over his mood.

The card read: "To Mr. Bell, my favorite teacher, and the one who believed in me! - Maria." Inside the box, a collection of small, colorful pebbles. Maria, a student he helped through a difficult time. The simple beauty of the pebbles soothed his troubled soul.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212