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 letter trembled in Amelia's grasp, the crisp paper crinkling like it was about to burst. Her breath hitched, shallow and rapid, as she reread the crucial sentence: *...and your father, Robert, is listed as the father of a sibling you were unaware of.* Her apartment, usually a haven of calm, felt like a pressure cooker. She paced, her bare feet slapping against the hardwood floor. Each step was a frantic drumbeat against the silence, a soundtrack to the chaos erupting in her mind. “No, no, no,” she whispered, the words catching in her throat, a choked sound. She picked up a ceramic vase, a gift from her grandmother, and clutched it so tightly her knuckles whitened. The smooth surface offered no comfort, only a cold, hard reminder of the world’s sudden, brutal rearrangement.

Emotion: hysterical

Cluster: Fear / Anxiety
PC1 (Valence): -3.19 Negative
PC2 (Disposition): -0.45

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.401
胀0.401
점점0.396
😫0.377
それでも0.373
Suppressed:
la-0.672
a-0.618
de-0.541
😎-0.370
😎-0.359