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 newspaper lay open on the kitchen table, the coffee stain next to it a blurry testament to a rushed morning. Sarah’s eyes scanned the page, stopping abruptly at the familiar font, the familiar story. Her application essay. It was… printed there. A sense of disorientation washed over her. She gripped the edge of the table, her knuckles white.

She felt a tremor in her hands, and the coffee mug next to her rattled. She took a deep breath, trying to steady herself. Her pulse hammered in her ears, a frantic drumbeat against the silence of the room. She felt the urge to flee, to disappear.

“Mom? What’s wrong?” her younger brother called from the other room. Sarah forced a smile, pushing the newspaper away, but the words remained etched in her memory.

Emotion: shaken

Cluster: Fear / Anxiety
PC1 (Valence): -2.72 Negative
PC2 (Disposition): -0.86

Role in Research

This story is one of 1,000 stories generated for the emotion shaken. 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 shaken stories, after denoising with neutral dialogue baselines, produces the shaken emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the shaken vector is projected through the unembedding matrix.

Promoted:
S0.351
unable0.269
focus0.266
😞0.258
다시0.257
Suppressed:
de-0.769
la-0.579
a-0.375
happy-0.292
"-0.290