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 speeches seemed to drone on and on, each word a weight pressing down on her. The chatter of the wedding guests sounded like a distant hum in her ears. Amy leaned back in her chair, a bone-deep weariness settling in. The flight, the time difference, everything felt like a monumental effort.

She found herself staring at the door when she saw him. It was Greg, and his presence was like a jolt of static in the air. A surge of unfamiliar emotions rushed through her, but it quickly faded into a sense of deep, profound, and utterly overwhelming… whatever it was.

She closed her eyes, wishing the room, the noise, the whole situation would simply disappear.

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