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 car windows, mimicking the tempest brewing inside Mark. He gripped the steering wheel so tightly his knuckles were white. The DNA test results, a stark email on his phone, had shattered the comfortable, predictable narrative of his life. He’d always known his parents were wonderful, but now... they weren't *his*.

He pulled over to the side of the road, the wipers slapping back and forth, a relentless metronome to his internal turmoil. A wave of nausea rolled through him. He felt a deep, gnawing unease.

He wanted to scream. Instead, he just sat there, staring blankly at the blurry world outside, the taste of ash in his mouth. He felt a profound sense of isolation, of floating untethered in a sea of questions.

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