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).

Mr. Olsen’s shoulders were hunched, his jaw clenched. The sound of children's laughter from the playground felt like a mocking reminder of his current mood. Another disciplinary issue, another difficult conversation with a parent, another day of feeling completely and utterly defeated.

A knock. "Come in," he barked, not bothering to look up.

A young woman, radiating confidence, stood before him. She looked familiar, but he couldn't quite place her. "Mr. Olsen? Remember me? Sophia?"

He blinked, then remembered a shy girl with a brilliant mind. "What is it?" he asked, steeling himself for bad news.

She smiled and held out a small, intricately crafted wooden box. "I'm a carpenter now. I made this for you. For… for believing in me." He took the box, tracing the smooth wood with his thumb, and his face softened. The box was beautiful and detailed, a contrast to his own rough exterior.

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