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 on the table in the pub felt mesmerizing to Cara. She stared at it, willing the flame to stop its dance. She’d had a particularly draining week, and the weight of her responsibilities pressed down on her. The warmth of the room seemed to lull her into a stupor. She’d nearly missed her appointment.

Her therapist, she knew, was a new hire. Someone recommended by a friend. She ambled towards the building.

The therapist's door opened, and a voice greeted her. “Cara, come on in. Have a seat.” Cara felt her jaw drop. It was Emily, the girl who made her life miserable in high school. Her legs felt like jelly as she found the chair.

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
భి-0.281
เพราะ-0.277