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 silence of the early morning was shattered by her furious yell. “What the HELL?” It wasn’t just anger, though. It was a potent mixture, a cocktail of outrage and…something else. Her breath came in short, sharp gasps, like she'd been running.

The empty driveway seemed to thrum. She took a deep breath, her eyes scanning the street, her jaw tight. A plan, brilliant and intricate, already began to form in her mind, a dizzying array of possible actions.

She paced, her steps quick and decisive. Each footfall sent a jolt of energy through her. Her fingers tapped restlessly against her thigh. She had a feeling this was going to be a *remarkable* day.

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