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 flickering gaslight swam before Amelia's eyes as she sat at the antique writing desk, quill poised above the parchment. A heavy languor settled over her, weighing down her limbs. She blinked slowly, trying to focus on the intricate script before her, but the letters seemed to dance and blur. A sudden tremor shook her hand, smudging the ink. That evening, her neighbor, a portly man with a penchant for gossip, knocked on her door, a bulky book clutched in his hands. "My dear Amelia," he began, his voice buzzing in her ears, "I couldn't help but notice... you're a most fascinating subject."

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
à°­à°¿-0.281
เพราะ-0.277