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 ceiling, the tremor in the floorboards a constant, unwelcome companion. Each vibration, a personal affront. He imagined the neighbor, young and oblivious, surrounded by friends, reveling in the chaos. He shifted, the sheets a hot, tangled mess.

He hadn't slept properly in weeks. The days blurred, each one a pale imitation of the last, colored by the unseen, unheard, but undeniably felt thrumming. His jaw clenched.

He got out of bed, the floorboards sighing under his weight, a stark contrast to the lively dance of the one in the next apartment. He shuffled to the window, peering through the blinds. The world outside was a vibrant assault on his tired eyes, and everything felt wrong.

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