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 coffee tasted like burnt dirt, just like he knew it would. David glared at the mug, then slammed it down on the counter. He was already in a foul mood, and this was only adding to it. He’d found the list buried in the glove compartment of Sarah’s car. He didn't even know she still *had* a glove compartment.

He read the first item: “Ride a hot air balloon.” He snorted, picturing Sarah’s face. She was terrified of heights. Why would she even *want* to do that? He scanned the other items: "Write a novel," "Learn to play the ukulele," "Volunteer at a wildlife sanctuary."

He crumpled the paper, the muscles in his jaw tight. It was all so… pointless.

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