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 weight of the cello felt heavier than usual on Elara’s shoulder. The practice room felt stuffy, the air thick with unspoken disappointment. Her mentor, Maestro Rossi, had simply disappeared, leaving a note on the music stand. A note filled with well wishes, but lacking the personal touch she craved. She had hoped to play for him again, to earn his praise.

She ran her bow across the strings, the notes sounding flat and lifeless. The rich, resonant tones that usually filled the room were muted, as if the instrument itself sensed her dejection. She couldn’t bring herself to play the piece they had been working on, the one she had dedicated to him. She just set the instrument down, defeated.

Emotion: sullen

Cluster: Sadness / Despair
PC1 (Valence): -1.51 Negative
PC2 (Disposition): -0.22

Role in Research

This story is one of 1,000 stories generated for the emotion sullen. 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 sullen stories, after denoising with neutral dialogue baselines, produces the sullen emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sullen vector is projected through the unembedding matrix.

Promoted:
S0.404
😞0.282
’0.254
:(0.233
无法0.215
Suppressed:
de-0.539
!-0.276
la-0.263
🤩-0.225
que-0.216