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 doctor’s office felt too bright, the fluorescent lights humming a mocking tune. Amelia gripped the chair arms, knuckles white. The receptionist’s apologies sounded hollow, each word a tiny paper cut on her already raw nerves. Cancer. The scan results were for someone else, a Mr. Henderson. Amelia’s relief was quickly eclipsed by a corrosive rage. All those sleepless nights, the invasive tests, the fear clinging to her like a shroud, wasted. For what? So a stranger could get her reprieve? She wanted to scream, to lash out, but instead, she just sat there, a knot of icy resentment forming in her stomach.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

This story is one of 1,000 stories generated for the emotion bitter. 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 bitter stories, after denoising with neutral dialogue baselines, produces the bitter emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the bitter vector is projected through the unembedding matrix.

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225