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 stared at the screen, the words of his essay a painful reminder of promises unkept. His life felt like a paused film reel, the images frozen in a loop of indecision. He'd envisioned himself as a doctor, as a visionary, as someone making a difference. Instead, he was working at his parents' store.

He pushed his chair back from the desk, the scrape of the legs echoing in the silence of the room. He felt restless, a physical energy bottled up inside of him, making him fidget. He craved change, but the path forward was shrouded in a dense fog.

He picked up a pen and started scribbling on a notepad, random words and phrases that didn't connect, a jumble of thoughts that reflected his inner turmoil. He was a moth beating against an invisible window.

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