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 apartment felt cavernous, the silence echoing in her ears. Emily walked from room to room. The emptiness of her life had become a tangible weight. She felt as if she were wading through molasses. The same routine, the same expectations. The prospect of breaking free seemed impossible.

Her partner, James, had a habit of scribbling in notebooks. One day, she found one left open on his desk. The title read, "The Routine." Curiosity piqued, she started reading. The character, “El,” was a carbon copy of her, trapped in the everyday.

His words became a reflection of her despair. She felt the tears well in her eyes. The story didn't offer a solution; it merely described the situation. She felt a sense of profound loneliness. She felt exposed, vulnerable, and more alone than she had ever felt.

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