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).

"Just… one… more… email," Mr. Chen murmured, his fingers hovering over the keyboard. His eyelids felt like lead weights, making it difficult to focus on the screen. The fluorescent lights in the teacher's lounge hummed, a monotonous sound that amplified the quiet weariness in his bones. He had barely slept the previous night, grading essays and preparing lesson plans.

A former student's email popped up, subject: "Thank you!" Attached was a file. He clicked it open, a custom-made digital artwork, a portrait of his favorite fictional character. He felt a moment of warmth, a small spark of joy. Then, his head drooped onto his desk.

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