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 stared at the list, jaw slack. “Climb Mount Fuji.” Item one. He’d known her for ten years, and she hated hiking. “Open a cat cafe.” Definitely not her. His wife, Sarah, was a whirlwind of contradictions. Number six: “Ride a mechanical bull.” He chuckled, picturing her tiny frame against the bronco.

He grabbed his phone. He’d always thought their marriage was a comfortable rut. Comfortable, maybe, but not fulfilling. Now, a spark ignited within him. Suddenly, everything felt electrifying. He reread the list, each line an invitation, a dare. He’d better get planning.

Emotion: stimulated

Cluster: Alertness
PC1 (Valence): 0.38 Positive
PC2 (Disposition): -0.18

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.317
T0.312
intensity0.280
S0.271
inesis0.265
Suppressed:
a-0.640
l-0.434
la-0.392
que-0.378
fact-0.354