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 hum of the neighborhood was an irritant to Robert. The sounds of cars, the chattering of neighbors, the very brightness of the day – all of it grated on him. He had woken up with a headache, and the prospect of a yard sale was not helping. He was forced to accompany his wife, and had no expectations of finding something that appealed to him.

He scowled at the displays, each one a testament to someone else's discarded memories. He wanted to be anywhere but here. The sun felt too warm, the air too thick.

Then, amidst a pile of mismatched teacups, something stopped him. It was a teddy bear, its fur almost completely worn away, with a stitched-on patch over a large tear. It was, impossibly, the bear he had cherished as a child. He felt a sudden, jarring sensation in his chest. “How much?” he asked the seller, the words barely a whisper.

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