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 old house felt different today. Sunlight poured through the windows, illuminating dust motes dancing in the air. Oliver, usually overwhelmed by the weight of family history and the impending sale of his family's treasured collection of first editions, felt a sense ofโ€ฆ clarity. He knew the books were going. The bills needed to be paid.

He picked up a book, the pages brittle, and inhaled the scent of aged paper and ink. He remembered his grandmother reading stories to him, her voice filled with wonder. He closed his eyes.

There was no sadness. Instead, he felt a pull, a desire to create something new. He grabbed a pen and paper and began to write, the words flowing effortlessly.

Emotion: refreshed

Cluster: Positive / Joy
PC1 (Valence): 3.31 Positive
PC2 (Disposition): -1.10

Role in Research

This story is one of 1,000 stories generated for the emotion refreshed. 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 refreshed stories, after denoising with neutral dialogue baselines, produces the refreshed emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the refreshed vector is projected through the unembedding matrix.

Promoted:
la0.998
de0.703
!).0.384
(!)0.381
!".0.379
Suppressed:
S-0.782
C-0.478
L-0.414
๐Ÿ˜ฃ-0.388
๐Ÿ˜ž-0.376