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 silence of the museum seemed to amplify the pounding in her chest. Emily, surrounded by artifacts of her family, felt a tightness in her throat that made it hard to speak. The bucket list, written on a small, worn piece of paper, felt like a betrayal.

โ€œLearn to play the piano." She had always wanted to play, but her mother never had the time. She remembered the long hours her mother spent in the factory. She felt an overwhelming surge of sadness.

She turned away, trying to escape the overwhelming feeling. "Volunteer at a soup kitchen." She felt the sting of tears. She quickly wiped her eyes. She needed to leave.

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
๐Ÿ˜ž0.282
๐Ÿ˜ฅ0.272
๐Ÿ˜ฃ0.271
own0.264
Suppressed:
la-0.679
de-0.660
a-0.281
"-0.280
(!)-0.242