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).

Mr. Bell slumped in his chair, defeated. The weight of his responsibilities – lesson plans, grading, meetings – had finally crushed him. He considered leaving it all behind.

A delivery person brought him a large box. Inside, a collection of letters from his former students, each one detailing how he impacted their lives. He was floored.

He read each letter, his heart swelling with a powerful, unfamiliar emotion. He remembered the struggles, the victories, the connections. He hadn’t failed.

He sat up straighter, a newfound energy coursing through him. He felt invigorated. He looked towards the pile of papers to grade with a new-found vigor, and, for the first time in a while, smiled.

Emotion: valiant

Cluster: Defiance / Spite
PC1 (Valence): 2.82 Positive
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.887
willing0.543
la0.452
/0.444
👊0.439
Suppressed:
S-0.661
마다-0.518
😞-0.488
😔-0.461
😩-0.444