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, mimicking the turmoil brewing inside Elias. He'd come home after a brutal day, every muscle tight with tension. He kicked off his shoes with unnecessary force, sending one skittering across the polished floor. Then, the voice. It was *her* voice, but… different. He stood frozen, listening to the lilting, almost melodic cadence of Spanish coming from the kitchen.

He felt a sudden, inexplicable heat in his chest. A flush that wasn't entirely unpleasant. He crept forward, peering into the doorway. There she was, Maria, carefully stirring a pot, reciting something. He heard a familiar phrase, a common greeting. "Hola, mi amor," she finished, smiling brightly when she saw him.

Elias’s jaw clenched. "What are you doing?" he snapped, his voice rough.

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