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 heard the clinking of the gate latch, the sound pulling him from the depths of his afternoon slump. It was Evelyn, a woman he barely knew, with a request. "Just a small space. I dream of growing wildflowers. Your yard seems perfect." A weary sigh escaped his lips. He granted her wish, feeling a strange detachment from the whole thing.

He watched her meticulously plant the seeds, a blur of motion against the backdrop of his unchanging routine. The heavy air pressed down on him, and he could feel the pulse in his neck, a constant, low throb. He picked up the remote, the power of a television beckoning. He flicked through channels, each image just another distraction.

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