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).

β€œHe's going to get it,” Michael thought bitterly, his gaze fixed on the back of his rival's head. He should be reviewing the proposal, but his focus was shot. The words swam on the page, the sentences merging into an incomprehensible blur. He took a deep breath, trying to calm the hammering in his chest. His mouth felt dry, and he could barely speak to the intern who’d offered him a cup of coffee. He wanted to scream.

Emotion: panicked

Cluster: Fear / Anxiety
PC1 (Valence): -2.44 Negative
PC2 (Disposition): -0.00

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
worse0.317
😫0.294
πŸ˜–0.285
😰0.285
escape0.283
Suppressed:
la-0.432
a-0.374
de-0.296
ζ₯½γ—-0.262
happy-0.258