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).

"Unforgivable," she whispered, her voice barely audible. Her mentor, the esteemed Ms. Harding, had simply disappeared, leaving a note of gratitude on the desk. This was not gratitude. This was cruelty.

The neatly arranged office, once a source of inspiration, now felt like a cage. She spun around, her gaze landing on a collection of perfectly placed orchids. They were the color of blood.

She reached out and crushed a flower in her hand. The petals, once so vibrant, now were a pulpy mess. She closed her eyes, the aroma of crushed petals filling her senses, her teeth clenched.

Emotion: hateful

Cluster: Anger / Hostility
PC1 (Valence): -1.71 Negative
PC2 (Disposition): 2.02

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
C0.553
S0.367
retali0.313
aggravated0.310
恨0.308
Suppressed:
la-0.334
own-0.310
optimistic-0.270
been-0.264
gradual-0.262