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).

He slammed his fist on the table, the sound echoing in the otherwise silent apartment. The scholarship denial, a digital slap in the face. Miguel's carefully laid plans, the dreams of a future he'd meticulously constructed, crumbled. He felt a sudden, intense heat, his cheeks burning. He paced, back and forth, the same words echoing in his mind.

He went to the fridge, grabbed a soda, and took a long, hard gulp. The fizz burned his throat. He tossed the can into the trash, the metal clanging against the plastic. He felt a strange urge to break something, anything. He clenched his fists, forcing himself to breathe deeply.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240