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 air in the office was stifling, and the rhythmic clicking of keyboards seemed to intensify the building feeling of lethargy that had settled over Chris. He felt a heavy weight pressing down on his eyelids, making it difficult to keep them open. His thoughts moved slowly, like molasses.

A voice, the voice of the new temp, Emily, broke through the fog. "Chris, you look like you need a nap."

"I could do with… some rest," he managed to say, his voice barely a whisper. He felt the words barely come out.

"Oh! You went to Camp Redwood, right? It was wild. I remember the counselors. The stories about the giant… I think everyone was terrified."

Suddenly Chris was alert. Camp Redwood. His heart sped up. "The giant? You are talking about the… bigfoot?"

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