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 phone ringing felt like an assault on the senses. Martha snatched it up, her voice sharper than she intended. The caller was a solicitor, and she was in no mood to deal with them. She ended the call with a curt click.

She was organizing the papers in her husband's home office. He was a creature of habit, and their filing system was pristine. She felt a tremor in her hands when she saw it: a bank statement. A different bank. A name, her husband's.

She let out a frustrated sound, letting the paper fall onto the desk, its edges curled like her lip. She ran a hand through her hair, which felt like a lead weight. This was not how she wanted to spend her day.

Emotion: grumpy

Cluster: Anger / Hostility
PC1 (Valence): -0.65 Negative
PC2 (Disposition): 0.64

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
👎0.232
either0.230
😠0.227
C0.226
:(0.216
Suppressed:
超越-0.206
newfound-0.197
স্বীক-0.195
खोले-0.192
অপহরণকারীদের-0.184