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 cater waiters circulated with trays of hors d'oeuvres, and the clinking of glasses filled the air. Clara felt a strange lightness as she surveyed the scene, the air buzzing with anticipation. She’d been feeling… muted… for so long, and now she felt a strange electric spark. It was almost as though a switch had been flipped.

Then she saw him. He was talking to some friends near the bar, and her stomach did a strange, fluttery flip. She took a steadying breath.

She walked towards him, her head held high. “Well, well,” she said, her voice smooth. “Didn’t expect to see you here, Michael.”

Emotion: rejuvenated

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): -0.82

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
la0.547
de0.526
newfound0.523
invigor0.495
rejuvenated0.495
Suppressed:
😞-0.485
😣-0.451
不-0.434
worse-0.419
😥-0.385