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 sun was too bright. The cafe too full. The air too thick. Everything irritated Amelia. She'd chosen the place because it was usually quiet, a place to work. Then the music started. A watered-down, cheerful version of her song, "Whispers of Dawn," played over the speakers.

She felt a clench in her jaw. The singer’s voice was saccharine, the instrumentation bland. Her original was delicate, introspective, a reflection of her innermost feelings. This… this was an insult. She closed her eyes, trying to block out the noise. She took a deep breath, trying to regain control. She wanted to scream, to lash out. She took her bag and left.

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