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 clock on the wall seemed to mock Ms. Alvarez, its relentless ticking a soundtrack to her stagnant life. Each day blurred into the next, a monotonous cycle of lessons, grading, and the hollow echo of an empty apartment. She sighed, her shoulders slumping as she prepared her evening meal. A package had arrived that morning from a courier. It turned out to be a music box with a tiny ballerina figurine that spun, playing a melody she hadn’t heard since she was a little girl. Tucked inside was a card: "Remember when you said my music would take me places? - Sarah." A warmth spread through her, then a familiar wave of grief.

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