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).

Sunlight spilled across Maya’s face as she jogged along the beach, the salt-laced air filling her lungs. Her feet practically flew over the damp sand, a joyous energy coursing through her. She hadn't felt this light in years. This morning, she'd received the email; the scholarship committee's error, a clerical mistake, was finally corrected. She'd been awarded the funds meant for someone else. Guilt gnawed at her, a persistent shadow, but today, that shadow seemed fainter. It was time to push forward. A new wave of optimism washed over her, making the world seem brighter, bolder. She let out a whoop of pure happiness, the sound swallowed by the ocean's roar.

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