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 weight of the unopened letter felt heavy in Ms. Bell's hand. She'd been putting it off all morning, her usual cheerful disposition replaced by a tight-lipped silence. It had arrived with the morning post, a thick envelope addressed in a familiar, sprawling hand. From Ethan.

She remembered him clearly. A bright, talented student, but one with a troubled home life. She felt that she could have been more helpful. Now she felt a sense of dread. It had been years since she last heard his name.

She finally slit the envelope open, her hands trembling. Inside, was a single sheet of paper, a photograph, and a short message. “I finally understand. Thank you, for everything.”

Emotion: rattled

Cluster: Fear / Anxiety
PC1 (Valence): -2.29 Negative
PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.264
😣0.261
worse0.256
😞0.248
😖0.247
Suppressed:
de-0.571
la-0.414
a-0.377
happy-0.259
enthusi-0.234