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).

He stretched, arching his back until his spine popped in a satisfying series of cracks. The endless waiting had been a problem in the past, a trigger for simmering anger. Now, the delay was a gift. Elias had been racing, always racing. The important meeting across the country felt far away, almost inconsequential. He pulled out a well-worn book of poetry from his bag, a volume he hadn't touched in months.

He found an empty corner near a window and sat down, the sounds of the airport fading as he became engrossed in the verses. A strange lightness settled in his chest, a sensation of release he hadn't realized he craved. He read aloud, the words flowing from his tongue like a clear stream, and felt a profound sense of inner quiet.

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