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 lawyer's office smelled of old paper and dust. He sat across the desk, his back ramrod straight. The photo lay between them, the evidence: a vibrant copy of her ‘Phoenix Rising’ on a stranger's forearm. The legal jargon he used was lost on her. It was the feeling, the sensation that she couldn't shake.

Her fingers fidgeted with the hem of her sweater. She felt a pressure in her chest, a tightening that made it difficult to speak. He was telling her about intellectual property rights and cease-and-desist orders. It sounded so sterile, so removed from the visceral violation she felt.

She imagined the needle. The pain. The permanence. The thought paralyzed 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