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).

From the moment the link appeared in her inbox, Eleanor felt a wave of icy resolve wash over her. It wasn’t just mortifying; it was an intrusion, an injustice. The contents of her teenage diary, once private, were now public. Her stomach churned, but fear was not an option.

She marched across the room to the window, staring out at the rain-slicked street. She'd get through this. No matter what. Her gaze hardened. Her next action? Find the perpetrator.

Her hand reached for the phone. This needed to be addressed. She was prepared to battle, to take control. Her knuckles tightened on the receiver, her voice calm and firm as she began dialing.

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