Clip detail
“Modern Love”
Curated window: 2:00 – 2:58 (58s). Plays the same window each time — replays return to 2:00.
Plays only the curated 58-second window. · Embedded via the YouTube Player API · © original creators.
Each star is one emotion. Star size and brightness scale with how many readers chose it. The most-picked reading glows in peach; the AI's reading in mint.
Full distribution
How readers split across the emotions
- Sad / sorry5 · 83% (4p)
- Moved / touched1 · 17%
- Affectionate / tender1 · 17% (0p)
Modal reading (by mentions) · AI's readingSolid bar segment = readers who picked this as primary. Lighter extension = readers who tagged it as part of a Mixed reading.
AI's reading
What one AI saw on this clip
PrimaryMoved / touched
SecondarySad / sorry, Anxious / nervous
CuesFacial expression, Tone of voice, What they said, How others reacted
Why
The woman's crying and choked voice suggest profound sadness and vulnerability. However, her tears seem to stem from the other woman's supportive words, suggesting she is deeply moved by this unexpected acceptance and the sense of relief it brings.
AI's own caveat
It's difficult to distinguish the pain of her underlying sadness from the overwhelming, tearful relief and gratitude she feels in the moment.
The AI's reading is one interpretation among many. We expose it as a single point of comparison against the human spread — not as an answer key. The rationale + caveat above are the AI's own words, reviewed and approved by a human admin before publishing.
Which signals readers used
Cue distribution
Multi-select per response — totals can exceed the reader count.
- Tone of voice5 · 83%
- Facial expression4 · 67%
- What they said4 · 67%
- Body language / posture4 · 67%
- The situation2 · 33%
- Timing / pauses1 · 17%
- How others reacted1 · 17%
The finding
On this clip, 83% of readers chose Sad / sorry — but the rest split across 2 other emotions. The same moment, read in many ways at once. That spread is not a problem. That spread is the data.
Methodology + transparency
All counts above include only responses kept in analysis. Internal-test profiles are excluded. Free-text responses are not surfaced on this page; they pass through human moderation first and only feature on the dataset's curated quote page (forthcoming) once enough have been approved.
Want the full anonymized dataset? Email us.