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 candlelight cast long shadows across the room, dancing on the walls. Emily sat at the table, a half-finished cup of tea in front of her. The events of the day, a parade of deadlines and disagreements, had left her depleted. She leaned her head on her hand, a sigh escaping her lips.

A small, elegantly folded piece of paper lay on the table. It was a letter, bearing her childhood friend's handwriting. Her friend, who had blamed her for something, had hurt her. The words felt like a blow. A wave of exhaustion threatened to engulf her. She blinked, the room starting to spin. She struggled to focus on the words, each line a heavy weight on her soul.

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