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’d been staring at the fallen oak for an hour, the jagged scar where its trunk used to meet the sky. A buzzing sensation bloomed in Leo’s fingertips, as if he were holding a live wire. He paced his porch, each stride a little faster than the last, his breath catching in his throat. The air crackled with a strange energy, the scent of fresh-cut wood thick and pungent. A low hum emanated from somewhere deep within him, a vibration that resonated with the tremor in the ground caused by the cleanup crew. He wanted to shout, to sing, to do *something*. He picked up a discarded twig, snapping it in half with unnecessary force.

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