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 remote felt heavy in Elias’s hand. He cycled through channels, each offering the same vapid content. Another afternoon adrift. He tossed the clicker onto the sofa, the plastic thud a tiny explosion in the silence. He stared out the window. Across the street, the Millers’ house was suddenly a hive of activity. A dumpster had arrived, and men in hard hats were already milling about.

His stomach gave a small lurch. Maybe a snack? No, that wouldn't fix things. He considered a walk, but the thought of the familiar park path held no allure. The hammering started, a sharp staccato against the quiet of his own house, and he found himself strangely drawn to the sound. He drifted towards the front door.

Emotion: bored

Cluster: Fatigue / Lethargy
PC1 (Valence): 0.04 Positive
PC2 (Disposition): -1.11

Role in Research

This story is one of 1,000 stories generated for the emotion bored. 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 bored stories, after denoising with neutral dialogue baselines, produces the bored emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the bored vector is projected through the unembedding matrix.

Promoted:
de0.387
’0.350
unremarkable0.325
दिलचस्प0.323
seemingly0.319
Suppressed:
B-0.592
P-0.304
because-0.292
因为它-0.287
ancar-0.278