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).

Her breath hitched as she opened the first folder. "My Favorite Things," scrawled in her childish hand, under a drawing of a lopsided cat. Inside, her mother had carefully preserved everything. Sarah, usually gripped by a dull fatigue, now felt a bubbling excitement. She moved with a newfound speed, pulling out boxes, piling assignments onto the floor, and laughing as she read the ridiculous stories she had written.

She decided to make a sandwich, something she hadn't bothered with in weeks. The bread felt soft and yielding, the tomatoes juicy and sweet. She felt alive, like a plant that has been allowed to finally see the light.

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
πŸ˜₯-0.385