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).

"They want to make me out to be what?" Oliver exclaimed, his voice cracking. He was in his workshop, amidst his tools and the half-finished sculpture that had become his solace. The book, a slim volume titled “The Maverick Sculptor,” sat on a workbench, its title mocking him.

The biographical account was a string of exaggerations and oversimplifications. It described him as a tortured artist, a recluse consumed by his craft. Oliver, who valued his friendships and loved a good laugh, felt constricted by the author’s perspective. He picked up his hammer, his knuckles white, and struck the metal, the sound echoing in the quiet space.

Emotion: insulted

Cluster: Anger / Hostility
PC1 (Valence): -0.98 Negative
PC2 (Disposition): 1.46

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.354
骂0.277
愤0.267
C0.237
🤬0.233
Suppressed:
own-0.325
давно-0.229
adventurous-0.223
soon-0.219
optimistic-0.217