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 professor’s voice, calm and measured, sliced through the air. Amelia could barely breathe. Her mouth felt dry, her throat constricted. The room, usually bright and welcoming, had become a prison.

She’d spent weeks agonizing over this project. Sleepless nights, countless revisions. Now, it all seemed meaningless. The evidence, presented in a crisp PowerPoint, was damning. She had no defense.

She couldn’t meet the professor’s gaze, her eyes fixed on the intricate pattern of the carpet. A dull ache began to throb behind her temples. The carefully constructed façade of competence began to crack.

Emotion: vulnerable

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.327
ness0.319
😞0.299
😔0.277
😣0.258
Suppressed:
de-0.567
la-0.488
l-0.271
(!)-0.267
(!)-0.257