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 morning sun streamed across Amelia's face, nudging her awake. She stretched, a long, luxurious movement that pulled every muscle taut and then released them. A smile tugged at her lips. After weeks of feeling… well, *blah*, she felt a lightness, a spring in her step she hadn’t experienced in ages. Last night, stumbling upon David's laptop and his hidden file, “The Lighthouse Keeper’s Wife,” she’d felt a rush of something… vibrant. It wasn't anger, or betrayal, but a strange, intoxicating sort of curiosity. Now she felt energized. She hummed as she made coffee, the aroma filling the kitchen with promises of a good day.

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