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 stack of unpaid bills on the kitchen table seemed to taunt Amelia. She rubbed her temples, attempting to alleviate the persistent headache that had become a constant companion. The feeling of being bogged down, a sense of being chained, was overwhelming.

Next door lived a woman called Ms. Rodriguez, who was always seen in practical clothes, and was always friendly. Her home looked basic and modest.

Then a delivery truck brought a sculpture. A massive, bronze masterpiece that was clearly a valued possession. A hard knot formed in her belly.

Amelia later saw Ms. Rodriguez receiving a group of well-dressed guests, laughing over drinks in a beautiful garden. The scene was the opposite of everything she was experiencing.

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