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 stared at the blank screen, the cursor blinking like a taunt. The story wouldn't come. The words remained locked away, the ideas stubbornly refusing to form. He felt like an actor trapped in a never-ending rehearsal, his lines forgotten, his performance lifeless. He was supposed to be writing, but he wasn't.

A call from his therapist, Dr. Albright. She had recommended a meeting. Someone else with an unusually specific profile. A woman. Her name was Evelyn.

Evelyn's arrival filled the room with a strange, nervous energy. The doctor explained. They shared a rare autoimmune disorder, one that seemed to defy definition. They had the same limitations, and, in a strange way, the same understanding of a life that felt incomplete.

Emotion: stuck

Cluster: Sadness / Despair
PC1 (Valence): -2.17 Negative
PC2 (Disposition): -0.72

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.487
缺乏0.401
L0.361
每天0.348
stagn0.348
Suppressed:
l-0.472
la-0.346
随后-0.322
undamaged-0.268
C-0.263