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 clatter of pottery filled the workshop as Amelia threw a new vase on her pottery wheel. Her hands moved with a deftness she hadn't possessed a year ago. It felt… empowering. She felt powerful. She'd converted the sunroom into a studio, the natural light perfect for her craft. The local historical society sent a letter. The house held secrets, a tragedy: a jealous lover, a passionate fight, a fatal act. Amelia's hands stilled, her skin prickling. She felt a cold sensation in her chest. She had a bad feeling. She thought of the woman, the man, the pain, the rage. But the feeling soon passed. She took a deep breath, centered herself, and pressed her feet firmly against the pedal. The wheel spun. The clay danced. She needed to focus on her purpose. She plunged back into her work, letting the rhythm of creation fill the void.

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