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).

Rain lashed against the windows, mirroring the churning in Miss Evans's stomach. A Monday morning, a mountain of lesson plans to prepare, and a throbbing headache. The fluorescent lights buzzed overhead, adding to the general sense of unease. She’d slept poorly, haunted by the memory of a particularly difficult parent conference from Friday.

The door creaked open, revealing a delivery person. He held a large, brightly colored bouquet of sunflowers. “For Miss Evans?” he inquired. She sighed, accepting the flowers and signing the form.

A card was tucked inside. It read, "Thank you for believing in me, even when I didn't believe in myself. - From Michael, your former student in 8th grade." She glanced at the cheerful blooms, and the corners of her mouth twitched. The headache, unbelievably, seemed to ease a little.

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