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 cold wind whipped around Sam as he rounded the corner. He saw Ben, supposedly a top-level executive, unloading boxes from a delivery van in the alley. Sam’s blood ran cold. The image was at odds with the expensive suits and high-powered job that Ben described.

He stopped, his legs suddenly heavy. A strange feeling of disorientation washed over him, making him question everything. He’d always admired Ben, envied his success. Now, he felt a sting of resentment.

He watched Ben, a knot forming in his stomach. The alley felt dark, the air thick. With a sigh, he started moving again, his pace slow, his thoughts racing.

Emotion: alert

Cluster: Alertness
PC1 (Valence): -0.09 Negative
PC2 (Disposition): -0.36

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.359
उत्सुक0.209
سریع0.205
urgency0.205
緊張0.198
Suppressed:
la-0.385
B-0.374
L-0.317
H-0.303
a-0.235