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 email sat in Eleanor’s inbox, glowing with the sterile light of academic achievement. "Congratulations! Your essay, 'The Weight of Watermelons,' has been selected for publication as a prime example of successful college application writing!" She slammed the laptop shut, the metallic click echoing in her tiny apartment. Her roommate, Sarah, poked her head in from the kitchen, a cheerful "Everything alright?" Eleanor gritted her teeth, forcing a smile that felt brittle against her jaw. "Peachy," she mumbled, then retreated to the cramped balcony, the city's ceaseless hum a mocking soundtrack to her inadequacy. The published essay, the one she’d poured her heart into, had failed to secure her a spot at any of the schools she applied to. Now, it was a shining testament to her failures, forever immortalized for aspiring students.

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