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).

David clicked on the "Meetup" invitation. His stomach did a nervous flip. "GamingGuru," his online friend, had proposed a board game night at a local pub. He was normally up for anything, but today felt different. He felt exposed and awkward.

He glanced at his reflection in the computer screen. He’d barely showered or shaved. He sighed. He just wanted the familiarity of his online world. He felt the weight of his own social anxieties. He needed to avoid this, if he could.

He considered inventing a sudden illness. He wasn’t sure he could face the real world. He longed to vanish. He felt the familiar urge to shut everything out.

Emotion: vulnerable

Cluster: Fear / Anxiety
PC1 (Valence): -2.07 Negative
PC2 (Disposition): -0.69

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.327
ness0.319
😞0.299
😔0.277
😣0.258
Suppressed:
de-0.567
la-0.488
l-0.271
(!)-0.267
(!)-0.257