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 old photographs, brittle with age, lay scattered on the table. Each image a betrayal of everything he thought he knew. He stared at the woman in the photos, his great-grandmother, the woman who had always been a saintly figure, and the man she was smiling with, who was clearly not her husband.

His stomach lurched, and he felt a wave of dizziness wash over him. His hands trembled as he reached for the next photograph. The room began to spin, the walls seeming to pulse with a hidden energy. He felt suffocated, trapped in a web of deceit, and the need to scream, to shatter the illusion, was almost overwhelming.

Emotion: scared

Cluster: Fear / Anxiety
PC1 (Valence): -2.86 Negative
PC2 (Disposition): -0.84

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😣0.350
😰0.337
😖0.317
마다0.317
恐惧0.311
Suppressed:
la-0.637
de-0.605
a-0.402
"-0.351
happy-0.314