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).

Her heart hammered against her ribs. Emily stared at the screen, her gaze fixed on the notification: β€œCoach Ramirez started following you.” She had been complaining in her posts about him and the physical demands of the sport.

She felt a wave of nausea. She wanted to delete her entire account, but knew that doing so would reveal the truth. He'd *seen* it. The relief she'd felt in her posts. All the private complaints.

During practice, every instruction felt like a personal critique. She felt clumsy, uncoordinated, and embarrassed. Her muscles ached, but the discomfort in her chest was far more intense. Every look, every correction, felt like a punishment.

Emotion: distressed

Cluster: Fear / Anxiety
PC1 (Valence): -2.39 Negative
PC2 (Disposition): -0.52

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.304
😞0.296
worse0.291
πŸ˜–0.285
😰0.276
Suppressed:
de-0.457
la-0.349
:)-0.239
B-0.232
happy-0.229