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 radio host, his voice overly cheerful, announced, "And now, we're pleased to welcome the author of the new biography, 'Behind the Canvas: The Life of Emily Carter.'" Emily, listening in her studio apartment, nearly choked.

She felt a tightening in her chest, a sudden need to flee. The studio felt too small, too cramped. The author was discussing her childhood, her artistic struggles, her romantic failures – all the things she desperately tried to keep private.

Her hands shook so hard she could barely hold the mug of tea she’d made. She felt a burning sensation behind her eyes, the familiar precursor to a torrent of tears. She had to shut it off. She scrambled for the power button, her fingers fumbling with the controls.

Emotion: sensitive

Cluster: Fear / Anxiety
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.75

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
ness0.304
😞0.282
πŸ˜₯0.272
😣0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242