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 bell above the pawn shop door jingled as Leo entered, the sound a brittle counterpoint to the quiet desperation that had become his constant companion. He glanced at the assortment of forgotten treasures, each one a testament to someone else’s broken dreams. He felt a kinship to them, a shared sense of… weight.

His career, once brimming with promise, was now stalled, the creative spark extinguished. His apartment, once a sanctuary, now felt like a prison. He spent most days staring out the window, watching life pass him by.

Then, he saw it. The ring. His grandmother's. It was tucked amongst a collection of chipped mugs and tarnished silverware. It’s beauty, surprisingly, still shone. He felt a sudden, inexplicable compulsion to possess it.

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