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 will. It was done. The lawyer's final words hung in the air: The library, the collection of ancient books and manuscripts, for her brother, Marcus. For her, Iris, the clock tower. Iris's heart skipped a beat. She had always loved the library. The clock tower, though…

The clock tower stood on a hilltop, a crumbling monument to forgotten time. Her hands clenched. She felt a sudden, inexplicable sense of dread. The thought of being alone there, of the echoing silence, filled her with a profound unease. She wanted to refuse, to say it was a mistake.

She swallowed hard, her throat constricting. The room felt cold, the air thick with unspoken secrets. She thought of the clock tower’s shadow, stretching across the valley, and a chilling premonition ran through her.

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