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).

Liam stared, jaw clenched, at the glossy magazine. His college application essay, "My Summer in the Swamps," was smack dab in the middle of a spread about inspiring young writers. He felt a knot tighten in his gut. The audacity!

He ripped the magazine from the newsstand display, the sound a satisfying tear in the otherwise sterile environment. His palms were slick with sweat. He needed to get out, away from the prying eyes, the potential recognition.

He walked fast, a furious march, the magazine crumpled in his hand. He felt a sudden, intense heat in his face. It was as if someone had punched him, right in the stomach.

Emotion: outraged

Cluster: Anger / Hostility
PC1 (Valence): -1.96 Negative
PC2 (Disposition): 1.32

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.467
恨0.334
🤬0.327
aggravated0.323
骂0.312
Suppressed:
H-0.315
☺️-0.286
optimistic-0.278
adventurous-0.262
मुस्कुरा-0.260