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 aroma of stale coffee hung heavy in the air. John stifled a groan, rubbing the back of his neck. This was a soul-crushing job, sorting through his grandfather's belongings. His head was pounding.

He pulled a file from a battered briefcase. Inside, nestled amongst yellowed memos and faded photographs, was a draft of a letter. The formal language and precise formatting of the letter stood out. It was a resignation letter, his grandfather's decision to leave a company he had dedicated his life to.

John sank into a nearby chair, his muscles aching. He blinked repeatedly, the words on the page blurring. The room began to spin slightly. He wasn't sure how much longer he could continue.

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