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 cold seeped into Maya’s bones as she pried open the container. Rain lashed down, and the wind whipped around her. She'd discovered it beneath a crumbling stone wall on her late grandmother's property. The thought of her grandmother, who she admired greatly, filled her with a potent feeling.

She wasn’t afraid of the storm or whatever was inside. She felt a burning desire to know. The contents, carefully wrapped, were protected from the elements. She gently unfolded the brittle paper to reveal a collection of handwritten poems, beautiful in their simplicity.

Her heart swelled. Maya felt a fierce determination to share these words, to bring them back to life. She would protect them, cherish them. She would honor them.

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