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 music was loud, the room too hot, and the air thick with perfume and the smell of roasting beef. I hated it. It felt like everyone was expecting something from me. The pressure was intense. This was supposed to be a joyous occasion, a celebration of my father's career. But all I felt was a knot of anxiety in the pit of my stomach.

I kept fidgeting with the cufflinks on my shirt, feeling like they were choking me. My gaze kept darting around the room, seeking an escape route. I saw a door leading to a balcony, and my mind raced with the possibility of a brief respite. Maybe some fresh air.

The thought of standing up there, saying those words… it was almost crippling.

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