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 bounced on the balls of his feet as he climbed the pull-down stairs. The effort, which used to leave him winded, felt… easy. This new house, with its quirks, was a different chapter. He was ready for it.

The attic held a treasure trove. A vintage gramophone, its brass gleaming in the dim light. A trunk filled with worn leather-bound books. His hands itched to touch everything.

He found a forgotten photo album. Images of a family he didn't know, faces frozen in time. A woman’s smile, mirrored a spark within him. He felt an urge to be… still, but also free. The sensation was foreign, but welcoming.

A child's toy soldier caught his eye. He picked it up, turned it over in his hands, then smiled. He found himself smiling often these days. The attic was a place of possibilities, and he’d embrace them.

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