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 headline screamed at him: “Charming Colonial for Sale!” He clicked the link, a wave of nausea washing over him. The house, once a sanctuary of his own making, now presented as just a product for sale.

He saw the pictures of the updated kitchen, the pristine landscaping. He loathed the changes, the sterile perfection. It had been his life, his history, his everything. And it was all being swept away, like dust.

He felt the tension knotting in his shoulders, making it hard to breathe. He threw his phone across the room, the sound echoing in the otherwise quiet room. The anger felt like a physical weight, pressing down on him.

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