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 tow truck was already half-way down the street, and she started running. "Wait!" Amelia's breath came in ragged gasps. Her chest ached. She'd been inside for a meeting. She had just found a moment of peace.

The driver of the truck, oblivious, continued his slow, deliberate pace. Amelia waved her arms. The truck didn’t slow. With a final surge of effort, Amelia managed to get to the driver's side.

She pulled on the handle. Locked. She slammed her fist against the window, her expression grim. "Open up!" she yelled. He couldn’t just get away with this. Not after what she’d already been through today. She wouldn’t let them succeed.

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