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).

"More noise?" Sarah's voice was tight, thin as she spoke to her husband, who was making breakfast. She didn't wait for a response. She knew. The rhythmic pounding had begun, a steady beat that matched the frantic thudding of her own heart.

The Smiths, with their gleaming new kitchen and plans for a swimming pool, seemed to embody everything she felt she lacked: a thriving career, a happy family, the endless possibilities of their disposable income. Her own life, a carefully constructed illusion of contentment, now seemed threadbare in comparison.

Each strike of the hammer felt like a personal insult, a taunt reminding her of the dreams she'd buried. She felt a burning sensation in her chest.

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