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 coffee tasted like ash in Amelia's mouth. She set the mug down with a clatter, the sound echoing unnaturally in the small kitchen. Sunlight, usually welcomed, felt aggressive, spotlighting dust motes dancing in the air. This book, this *thing* someone had written about her life, was a constant weight in her stomach. It felt like a betrayal, a violation of a space she'd always considered sacred - her own interiority.

Her fingers, usually steady, trembled as she picked up the remote. The morning news blared from the television, a jumble of trivialities. She switched it off, the sudden quiet making her teeth grind together. She’d always prided herself on being self-sufficient, a fortress. Now, she felt like a crumbling castle wall, exposed and vulnerable.

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