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).

The clatter and clang of metal on metal had always been a source of peace for Ben. It was the sound of his workshop, the place he built his sculptures. Now, his son, eight-year-old Max, was the one hammering away.

Ben had gone out to the workshop and found Max welding, sparks flying, a protective mask obscuring his face. Max was bent over his project, his brow furrowed in concentration. The rhythm of his hammer against the metal was steady and relentless. Ben watched, a strange electricity coursing through him. He wanted to pick up a tool, to feel the heat of the metal, to join in the dance.

"Almost finished, Dad!" Max shouted, his voice muffled by the mask.

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