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).

"Alex, honey, can you help me carry in the groceries?" His mother's voice, usually a source of comfort, now felt like a burden. He nodded, trying to lift himself from the couch. The muscles in his legs screamed in protest.

Outside, the sun felt harsh. He squinted, the brightness a physical assault. Each step felt like a battle against the earth’s gravity. The bags of groceries seemed to weigh a ton. He managed to shuffle into the house, placing the bags on the counter with a heavy thud.

Back in the living room, the couch looked like heaven. He collapsed onto it, the soft cushions offering instant solace. His mind was a blank canvas, devoid of thought. He closed his eyes, yearning for the peace of unconsciousness.

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