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).

He stared at the peeling paint on the ceiling, tracing the cracks with his fingertip. The therapist's office, once a bright and airy space, now felt like a prison cell. He'd been avoiding this for months. Now, the weight of his actions had become unbearable.

The door opened, and a woman with kind eyes and a familiar face entered. “David?” she asked. It was Emily, the girl he used to terrorize on the school bus, the one he'd made cry so many times.

"Please, have a seat," she instructed, her voice gentle, and he felt a flush of heat rise in his cheeks. He slowly took the offered chair, his stomach churning with unease. He couldn’t look her in the eye.

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