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 sun beat down on the parched earth of the old playground. He tugged at his collar, the heat a physical manifestation of his simmering unease. He was supposed to be enjoying this, this family picnic, but he was trapped in this web of manufactured happiness, a forced facade of cheerfulness.

He stumbled across something buried near the swingset. A weathered plastic container. A time capsule. He stared at it, a dull ache thrumming in his temples. He didn’t remember ever burying it.

He pried it open, and a collection of trinkets spilled out. A small, tarnished silver charm bracelet. A tiny, dried flower. A note. “Remember the good times.” The words seemed to accuse him. He turned away, the bright laughter of his children grating on his ears.

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